\name{NEWS}
\title{NEWS file for the survival package}
\section{Changes in version 3.4-0}{
  \itemize{
    \item Replace .[terms call in predict.coxph with drop.term();
    due to an error in [.term discovered by Jorge Menezes.  Add
    dropterm.R to the test suite.
    \item Fix all errors in R CMD check, and submit to CRAN
}}
\section{Changes in version 3.3-2}{
  \itemize{
    \item Error in concordance(fit, newdata) if newdata had missing
    values: the derived x and y could be different lengths.
    \item Add test cases for the (rather difficult) case of predicted
    survival for multi-state coxph model that has shared hazards
    \item nsk(..., Boundary.knots=FALSE) was not being handled properly.
    \item Fix error in terms.inner; it failed for a function with no
    arguments. Pointed out by Daniel Sjberg and Duncan Murdoch.
    \item Remove Sint from C code.
    \item The package sometimes used P(>Chi) and somtimes Pr(>Chi) as a
    printout label; the base packages all use "Pr".  Changed this to be
    consistent.
    }}

\section{Changes in version 3.3-1}{
  \itemize{
    \item Update the saved tests/Examples/survival-Ex.Rout.save file so
    as to remove timings, at the behest of CRAN.  (Footnote 21 in the
    packages manual talks about this.)
}}
\section{Changes in version 3.3-0}{
  \itemize{
    \item Change any calls to Calloc or Free in the C code to R_Calloc
    and R_Free, at the request of R core.
    \item Fix an oversight in aareg: when coxph and survreg were
    converted from using +cluster() in a formula to cluster as an
    argument, that same change needed to be made in aareg.  Pointed out
    by zdgager.
    \item The std of the cumulative hazard is now present, for select
    cases of a coxph model curve.  More work remains to be done to
    return the std for all cases.
    \item Add a paragraph to the help page for survfit.Rd, pointing out
    that robust variance is now the default for interval censored data,
    and why.
    \item Add the median.survfit method
    \item Improve the examples in pseudo.Rd
    \item Fix error in survreg.distributions$gaussian$deviance. The
    deviance of an interval censored observation was NA due to a sign
    that was backwards, leading to log of a negative value.  (Simple
    typo.)
    \item Error in predict.coxph: it would fail for a model that had two
    strata terms. Reported by Hanna Frick.
    \item Fix github issue 130. If newdata contained the strata
    information, and there was only one curve requested, survfit.coxph
    would return too many curves.
}}

\section{Changes in version 3.2-15}{
  \itemize{
    \item Fix an inconsistency with the start.time argument.  One of
    the survfit paths would include an event at start.time (curve starts
    with an immediate drop) others did not.  All paths now do so. This
    makes start.time=0 behave the same as ordinary survfit, without the
    argument, when there is a death at time 0.
}}

\section{Changes in version 3.2-14}{
  \itemize{
    \item Update the royston function to report the scaled Cox-Snell
    R-squared as the Nagelkirke estimate, and clarify the documentation.
    \item Update for coxph with ties=exact, for the case of an infinite
    coefficient where the information matrix becomes singular.  Code for
    this case had been developed for coxfit6.c (Breslow/Efron) but not
    replicated in coxexact.c
}}
 
\section{Changes in version 3.2-13}{
  \itemize{
    \item Clarify some sentences in tmerge help file.
    \item Fix a memory access error in concordance3.c, found by CRAN.
    \item Add the drop.special function (internal) to work around offset
    problems in [.terms.
}}
\section{Changes in version 3.2-12}{
  \itemize{
    \item Avoid a downstream error from infinte coefficients in
    coxph.  In special case it would fail by passing an NA to C code.
    \item The df column from cox.zph could be incorrect for a coxme
    model.
    \item cox.zph would crash for a coxme model whose random effect
    contained a factor (odd issue with model.frame).
    \item yates error for a coxph model with a strata * covariate
    interaction
    \item Clarify documentation for the royston command.
    \item Add error for survexp applied to a multistate model.
    \item Make the labeling of restricted mean consistent in print and
    summary, for single state and multistate survfit.
    \item With just the right data the coxexact.c routine would do a
    very inefficient calculation: so slow it appeared to be an infinite
    loop.
    \item Bug in pspline.R: I had neglected to include 'degree' in the
    retained arguments for makepredictcall.
    \item Fix scale factor error in cholesky3.c, which could cause it to
    incorrectly mark a column as singular.  Found via a survreg example
    from Nathan Adams, where y had large values.
    \item 2021-08-12: update CRAN
}}
\section{Changes in version 3.2-11}{
  \itemize{
    \item Missing labels for the "pairwise" option in yates(), fixed.
    \item Bug in plot.survfit -- could not use conf.int=T and xmax in
    the same call.  Pointed out by Dirk Larson.
    \item Failure of survfit, when applied to a multi-state coxph model with
    strata().  Repaired and added this as a test case.
    \item Change seq(along=  to seq(along.with=, to match the complete
    argument name.
    \item In pyears(...,data.frame=TRUE), if the levels of a tcut are
    numeric return a numeric rather than a factor.  (Version 2.4 feature
    that had been inadvertently removed.)
    \item Fix mistake in survfit.coxphms(..., stype=1): had pmin when I
    meant pmax.  (Resulting curves were not even close.)  Add a test
    case.
    \item update anova.survreg to have class("anova", "data.table").
    Error pointed out by Daniel Sjoberg.
}}

\section{Changes in version 3.2-10}{
  \itemize{
    \item CRAN valgrind checks discovered an uninitialized vector in
    one of the C routines.  Now fixed.  Updated version is now on CRAN.
}}

\section{Changes in version 3.2-9}{
  \itemize{
    \item More careful tests of the rttright function.
    \item Fix bug in tmerge that was introduced in 3.2-8. A new
    consistency check was too aggressive and would flag a legal dataset.
    \item Fix tmerge bug reported by E Lundt: if two or more additions
    were before the start of a subject's timeline, tdc would pick the
    first rather than the last.
sou    \item Add the last test case for residuals.survfit (auc for tstart,
    tstop data), and yes, it uncovered an error.
    \item Error in survit.coxph for a multistate fit with strata, an array
    dimension was wrong (but contents correct).  It led to downstream
    problems with print and plot.  Pointed out by Matthew Hall.
    \item Add ability for a multistate coxph model to have shared
    (proportional) baselines for transitions.
    \item The coxph routine no longer recenters 0/1 predictors (fit$mean
    will be 0), per the default value of the new \code{nocenter}
    argument. Application of survfit to a coxph model without specifying
    newdata remains a bad idea, but this change makes it a little
    less bad since for factors the curve will refer to the reference
    level.  The results of predict(fit) are now more defensible for a
    factor variable.
    \item Add an explicit error message for survreg() with a frailty
    term.  This usage was never supported -- it is integrating out the
    appropriate density for a coxph model, which is the wrong one for
    survreg -- but because the code would run we've found that people
    assumed it must be right, despite a statement to the contrary in the
    survival vignette.  Long overdue fix. 
}}
\section{Changes in version 3.2-8}{
  \itemize{
    \item In tmerge, if data2 contains identifiers not found in data1
    these rows are now counted in the "missid" column of the tcount
    attribute, rather than treated as an error.
    \item In a survfit() call with the start.time option, if one curve
    had no subjects past the start time the dim of the result was wrong,
    leading to multiple downstream failures.
    \item Add a scale argument to quantile.survfit.
    \item Revert a change to plot.survfit, which was the use of clip() to
    keep lines away from the right margin.  This had some unforseen downstream
    consequences, e.g., later addition of a legend.
    \item Minor fix to survcheck: if the events table had only 1 row the
    matrix property was lost. Pointed out by Oleguer Plana-Ripoll.
    \item Error in plot.survfit: the noplot argument had been overlooked
    for the confidence intervals, and the wrong interval could be matched to
    each curve.
    \item The neardate routine implicitly assumed that data set 2 was in
    sorted order, if it is not an error message ensues from the internal
    call to findInterval.  Now repaired and a new test added.  Pointed
    out by Bruce Macwilliams.
    \item Add an error message to survfit recognizing that it can not
    yet deal with multistate coxph models that have shared baseline
    hazards.
    \item Add the pseudo function for psuedo-values. The vignette is in
    vignette2 since it uses svyglm (survey) to get proper standard
    errors (see the 'other' vignette).
    Add supporting routine residuals.survfit (which does the real work.)
    \item Add the nsk function.
    \item Add the aggregate.survfit method
    \item Formally depricate survConcordance, replaced with the more capable
    concordance method which has formula, lm, glm, and coxph methods.    
}}

\section{Changes in version 3.2-7}{
  \itemize{
    \item Fix one URL, revealed by the CRAN submission.
    \item Column labels had been lost on the riskmat argument of
    coxph.detail, which broke the linERR package.  Found in reverse
    dependency checks for CRAN.
}}
\section{Changes in version 3.2-5}{
  \itemize{
    \item Fix error in summary.coxph.penal; it was incorrectly copying
    se(concordance) to the new object.
    \item Minor error in survfit.coxphms; it would fail if the model had
    an NA coefficient.
    \item Relax a check in concordance, to allow comparing two models
    with the same subjects but different response vector.
    \item If multiple strata() terms were first in a coxph model, the labels
    of the assign component would be incorrect, which affected labeling of
    cox.zph results (numeric values were correct, however).
    \item The riskmat option of the coxph.detail command now returns the
    matrix in data order rather than time-sorted order.
    \item The summary.survfit function had overlooked the std.chaz
    component when subsetting based on the times argument.
    \item The documentation for print.survfit stated that rmean="common"
    would use the largest time across curves, the code had the median.
    Make code agree with the documentation.  Pointed out by Qingxia Chen.
    \item Add the rttright function (redistribute to the right) and the
    R^2 measure of Royston and Sauerbrei.
    \item Add residuals.survfit, which will be important for
    pseudo-values.  Still incomplete.
    \item Better hardening of coxph against a particular kind of skewed
    variable, based on a test case from Michael Young.  This had led to the
    "This should never happen, please contact the author" message.
}}

\section{Changes in version 3.2-4}{
  \itemize{
    \item Add na.omit to the output of survcheck.
    \item Undo an ifelse typo (added in 3.2-3) in survexpm that caused it to
    return NULL for an upper triangular rate matrix, breaking survfit
    for a multi-state coxph model.  (Upper triangular has the simplest
    algorithm, and all the tests in the suite were for the more complex
    cases of course -- aargh.)
}}

\section{Changes in version 3.2-3}{
  \itemize{
    \item Fix error in survfit.coxphms: an internal routine was being
    called with arguments in the wrong order. 
    \item Add support routines for the derivative of a matrix
    exponential, needed for survival curve variance (post Cox model).
    \item Add explicit error message to summary.survfit, when the times
    argument asks only for times beyond the end of a curve and extend=FALSE.
    \item Clipping could be too tight in plot.survfit.  
}}

\section{Changes in version 3.2-2}{
  \itemize{
    \item Add support for "timeline" style survival data.  I
    hope this will be a step forward in usability for multi-state
    models, since data sets can be built with standard data manipulation tools.
    \item Fix error in survfit.coxphms, the weight vector could be the
    wrong length when the start.time option was used.
    \item Formulas in a multistate coxph model can now have "-x1" to
    delete variable x1, in secondary formulas.  (Update.formula is now used
    behind the scenes).
    \item Multistate coxph models now handle strata in full generality
    -- a stratum can apply to all transitions or just to some.  One
    consequence is that the cmap element of the returned fit has been broken into
    two portions: stratum_map contains strata information and cmap the
    coefficient information.
    \item Revert (partially) a change to tmerge. Using tdc() to update a
    variable that already exists in the baseline data was a problem, so
    tdc had been changed to replace rather than update.  Now allow updates to
    variables created by a prior tdc.
    \item Fix error in survfit, 0/1 status variable: the start.time
    option worked correctly only if the data set was sorted by time,
    which unfortunately was true of the test data in tests/survtest.R.
    Fix code and strengthen the test.
    \item Multiple updates to multi-state coxph models + follow-on
    curves. A current clinical project is providing a stress test.
}}

\section{Changes in version 3.1-12}{
  \itemize{
    \item Change the default for a robust variance: if there is a
    cluster argument, non-integer case weight, or an id statement and
    at least one id has more than one event.
    \item cox.zph would fail if the coxph fit had NA coefficients
    (something that used to work).  Add a test case to futureproof
    this.  Caught by Ville Ponkilainen.
    \item Minor: pyears + data.frame option would not preserve the order
    of factor levels from a tcut operator.  
    \item Edge case from Andrea Jaensch: a coxph model with strata +
    psline terms, plus a (time1, time2) data set containing observations
    that do not overlap any events, in just the right spot, could cause an
    infinite loop in agmart3.c.
    \item Add subset and na.action arguments to survcheck.
    \item Minor updates to plot.survfit and survcheck.
    \item Add cluster= option to replace +cluster() in a formula.
    Remove all mention of the latter from documentation and
    examples. Make the cluster, id, and robust options consistent across
    all the functions.
    \item Fix bug in plot.survfit with xaxs='S'.  At some point one line
     of code got lost.  
}}

\section{Changes in version 3.1-11}{
  \itemize{
    \item Add 'n' vector to survcheck, update tests.
    \item Improve multistate coxph printout
    \item Fix a memory reference error in multicheck.c
}}

\section{Changes in version 3.1-10}{
  \itemize{
    \item Fix error in concordance(fit, newdata= xxx): it used the old
    data at one point.  Pointed out by Matjin van't Hooft.
    \item Minor update to tmerge -- print a warning when a user attempts
    to update a variable using tdc, namely that this results in complete
    replacement of said variable, with no retention of prior values.
    \item Minor fixes to plot.survfit, when both xlim and xaxs='S' are
    specified.  Error and suggested fixes from Heinz Tuechler.
    \item Two failures in makepredictcall.pspline, found by 2 different
    users, both cases of options that should have been carried forward.
    A subsequent termplot() call failed if pspline had 'nterm' or
    'combine'.
    \item Fix memory leak (forgotten PROTECT) in zph[12].c; caught by B Ripley
}}

\section{Changes in version 3.1-9}{
  \itemize{
    \item The plot.cox.zph function would fail for a stratified model,
    if some covariate was a constant in one of the strata.  The cox.zph
    routine correctly labeled those points as uninformative via NA, the
    plot routine needed to actually ignore them.
}}

\section{Changes in version 3.1-8}{
  \itemize{
    \item For a multistate model with no covariates, the start.time
    value (if present) was inadvertently omitted from the result.  This
    affects the default plot.
    \item Per user request, the tmerge function can now use Dates as the
    time variable for the merge.
    \item Fix an invalid read (one element past the end of a vector)
    that could occur in tmerge.c; reported by Brian Ripley.
    \item A multi-state coxph model with strata would fail when parsing
    the formula, pointed out by Martin van't Hooft. 
}}

\section{Changes in version 3.1-7}{
  \itemize{
    \item For a coxph model with covariate*strata interactions the
    information matrix will be block diagonal, and the cox.zph function
    would generate a 0/0 when scaling it for plots.  This led to a
    BLAS error on some architectures (reported by B. Ripley within 24
    hours of 3.1-6 being published on CRAN).  Tests were unaffected,
    subsequent plots fail due to an infinite axis.
    Repair, and add more checks to the test suite.
}}

\section{Change in version 3.1-6}{
  \itemize{
    \item Repair issues in coxph.getdata and lines.survfit that were
    found with reverse dependency checks
    \item Submit to CRAN
}}

\section{Changes in version 3.1-5}{
  \itemize{
    \item Update coxph.getdata and coxph.detail to work with coxphms
    objects.  A deficiency in the first affected cox.zph results for
    multi-state coxph fits.
    \item Add a formal test suite for the cox.zph routine.
}}

\section{Changes in version 3.1-4}{
  \itemize{
    \item Move some vignettes to the vignette2 directory, found on the
    github website.  Add an index to those files.
    \item Add the timefix option to coxph results, and ensure that
    downstream survfit calls correctly retain it.
    \item Expand the main survival vignette.
}}

\section{Changes in version 3.1-3}{
  \itemize{
    \item The results of anova.coxph were incorrect for the case of a
    single model with ties="breslow" and tied event times: the breslow
    option was not being passed forward to the secondary fits.
    \item Add more sanity checks to anova.coxph, e.g., all models must
    have used the same ties option.
    \item Update tmerge to allow more variable types as the argument to
    tdc.  A user pointed out that Dates were not preserved; now fixed.
}}

\section{Changes in version 3.1-2}{
  \itemize{
    \item The cox.zph command now refuses models with tt() terms, before
    it had an incorrect computation.
    \item Fix 2 errors in plot, for survfit of a coxph model. (I had not
    scanned the pdf pages from the vignettes, which is the only way to
    verify plots.)
    \item Fix labeling error for combination of pyears, tcut variable,
    data.frame option.  (The numerical values were correct).
}}

\section{Changes in version 3.1-1}{
  \itemize{
    \item Fix error in [.cox.zph, when applied to a stratified model
}}

\section{Changes in version 3.1-0}{
  \itemize{
    \item Respond to some CRAN queries and resubmit.
    \item Better documentation of the survfit0 routine
    \item Add the sas.Rnw vignette to inst/doc: it takes too long to
    run for inclusion in the vignettes directory
    \item Fix two edge case errors pointed out on github: coxph on a
    data set with 0 events, and models with only a frailty term
    \item Update residuals.coxph to deal with larger matrices, i.e.,
    change two .C calls to .Call
}}

\section{Changes in version 3.0-11}{
  \itemize{
    \item Multiple small updates, after running tests for all
    reverse dependencies
    \item Send to CRAN
}}
  
\section{Changes in version 3.0-10}{
  \itemize{
    \item Make sure all calls to data.frame explicitly select a value
    for the stringsAsFactors option.
    \item Updates to cox.zph for the singledf option
    \item Add formal test of the cox.zph statistics
    \item Add the sas vignette to the vignettes2 directory (it takes too
    long to run).
}}
\section{Changes in version 3.0}{
  \itemize{
    \item Major revision of the survfit routines, see the survival vignette.
    \item Allow multi-state coxph models.
    \item Rename remaining .S files as .R
    \item vcov of a survreg object now contains dimnames (important for the
    stats::confint function)
    \item Subscripting survfit object removes the na.action.  This is a
    loss in the sense that the printout no longer tells us that
    observations were removed, but the information about which and how
    many rows were removed was incorrect after the selection.
    \item The survexp function, applied to a coxph model with strata,
    would sometimes produce extraneous y=0 values at the start of a
    curve.
    \item Multiple small bug fixes.
}}
\section{Changes in version 2.44-1}{
  \itemize{
    \item Fix error in survreg when the init argument was used.
    \item B. Ripley found/fixed an incorrect size in survfitkm.c, that
    could lead to memory overwrite and a hard crash. 
}}

\section{Changes in version 2.44-0}{
  \itemize{
    \item Add several data sets from the reliability literature, which
    had been used in the tests directory, to the package's
    data and add a help page of 'reliability'.
    \item Fix error in residuals.survreg, type="matrix", pointed out by
    Achim Zelies.  Another check has been added to the tests.
    \item The survfit routine now returns the cumulative hazard along
    with its standard error, and allows for robust variance.
    \item For (start, stop) data, the survfit result only includes
    unique stop times.
    \item Update plot.survfit to plot the cumulative hazard when
    fun='cumhaz', rather than plotting log(surv).
    \item The Nagelkirke R^2 has been removed from summary.coxph.
    The shortcomings of this measure are well known, concordance is a
    better measure.
    \item A cluster() term is not allowed in the finegray function; now
    give an explicit error message to that effect.

    \item Track down a failure that occured with some infinite
    coefficient data sets.  When iterations run out, the routine now
    returns the last successful iterate rather than the last attempt, e.g.,
    if the loglik maximizes at infinity the routine now returns the
    last step at which the partial likelihood, first and second
    derivatives were all finite.  This stops some downstream
    "non-finite" messages.

    \item Add concordancefit function to help pages and exports, so
    other packages can more easily invoke it.  
}}

\section{Changes in version 2.43-4}{
  \itemize{
    \item Added a hex sticker.  It is found in man/figures.
    \item Small grammar changes in a help page.
    \item Fix bug pointed out by A Ruten-Budde.  The coxph routine was
    not passing the timefix option forward to a subseqent concordance
    call.
    \item Fine tune the checks for an infinite coefficient.  A data set
    from rehbergT managed to have overflows in the first and second
    derivative at the same iteration, leading to an update of inf * 0.
    \item Formally add some small reliability data sets to the package, with a
    help page of 'reliability'.  They had been used in the tests.
  }
}

\section{Changes in version 2.43-2}{
  \itemize{
    \item In concordance, allow y to be an orderable factor (either
    is.ordered=TRUE or it has only 2 levels), instead of giving an error
    message.  Repair some missing references in the vignette.

    \item Fix an error check in survSplit, when the response has missing
    values.  The routine would fail with an error message when there was
    no error. (Pointed out by  Daniel Wollschläger.)

    \item Fix serious error in the finegray function when called with
    (start, stop) data, e.g., with time-dependent covariates: the
    censoring distribution G was incorrect which leads to incorrect weights,
    including NA.  Pointed out by Deqiang Zheng along with an example.
    (The use of time-dependent covariates in a FG model has serious -- I
    think fatal -- statistical issues, however.  The FG approach adds
    extra 'imputed' follow-up to each subject; but what is the future
    value of a time-dependent covariate over this new interval?)

    \item Update the finegray function to allow case weights.  If the
    original data has sampling weights, for instance, this propogates
    them properly to the created fgwt variable. 
}}

\section{Changes in version 2.43-1}{
  \itemize{
    \item Minor change to the concordance method to better accomodate
    another package; add one more test case as well.
    \item Change coxph to use concordance() rather than survConcordance.  
    Be aware that this changes the default variance estimate (to a
    better estimator however).
    \item Add a test to verify that tmerge works with Date objects as
    the time scale
    \item Add timefix=TRUE option to survdiff
    \item Add code for an edge case to coxph: a data set with no events.
}}

\section{Changes in version 2.43.0}{
  \itemize{
    \item Finish test suite and vignette for concordance.
    \item Run the tests for all packages that depend on survival.
    Submit to CRAN
}}

\section{Changes in version 2.42-7}{
  \itemize{
    \item Add arguments to survfit: survfit.matrix did not have
    start.time, and survfitCI did not have p0.  Now both of them have
    both.

    \item Fix two small errors triggered by the new checks for the use
    of && or || with arguments whose length is >1.  Pointed out by
    Martin Maechler.

    \item Add the concordance function, an upgrade of the older
    survConcordance function.  The latter will be depricated.  (The draft
    vignette still needs some polish.)

    \item Change survreg so that a returned "y" in the object is the
    original response, not the transformed y used for computation. This
    was prompted by the concordance.survreg method, but is also more
    consistent. It forced a change in residuals.survreg and uncovered
    a long standing bug for any fit that had specified y=FALSE. 

    \item Fix bug pointed out by C McCort: tmerge with "tdc(time, x)"
    would fail if x is of mode character.  Add this case to the test suite.
}}

\section{Changes in version 2.42-6}{
  \itemize{
    \item Remove the cbind.Surv and rbind.Surv methods. 
    The problem is when one is called with mixed arguments, e.g.
    cbind(Surv(1:4), data.frame(x=6:9, z=c('a', 'b', 'a', 'a'))
    In the above cbind.Surv is never called, but the \emph{presence}
    of a cbind.Surv method messes up the default behavior, see the
    Dispatch section of help('cbind').
}}

\section{Changes in version 2.42-5}{
  \itemize{
    \item Add a plot.Surv method per the suggestion of Goran Brostram.
    Improve the cbind.Surv and rbind.Surv methods to handle mixed
    argument lists (when there are some Surv arguments and some not). 

    \item Add a Survmethods.Rd page documenting the added methods.

    \item Add "F" and "S" to the list of fun= arguments to plot.survfit,
    they are aliases for "event" and "identity", respectively.
}}
\section{Changes in version 2.42-4}{
  \itemize{
    \item Undo a bug that was introduced in tmerge in 2.42-3; an essential
    line got commented out with the result that if sequential tmerge calls
    modify the same variable only the final change was retained.  Add a
    check to the test suite to prevent this in the future.

    \item Improve multi-state survfit when the input data has extra
    censored rows, e.g., a subject with transitions to state 1 at time 2
    and state 2 at time 8 but data of (0,2,1), (2,5,0), (5,8,2); the
    survSplit routine often generates such rows.
    Formerly the transitions table in the output would be incorrect for
    this case, and the life table would get an extra "censoring" line at
    time 5.  The estimated P(state) and its se was correct.

    \item Fix an edge case in tmerge, when using cumevent and the input
    data has a 'censored' row.  Add a test for this, and for another edge
    case of repeated updates at the same time point.

    \item repair xtfrm.Surv: it had returned a partial ordering for
    survival objects (like order()), it instead needs to be the analog
    of order(order(x)), a vector of integers with the same sort order as
    x.  Add test cases and a manual page.
    
    \item Add more Surv methods: head, tail, rep, rbind, c, rev, t,
    mean, median, plot, points, lines, levels. 
  }}

\section{Changes in version 2.42-3}{
  \itemize{
    \item Remove the coxph warning "X matrix deemed to be singular".
    The coefficients are NA, just as before, we simply say less.

    \item Fix minor bug in coxph: a covariate that was a constant would
    have its coefficent reported as 0 rather than NA, if (and only if)
    it was the only variable in the model, e.g.,
    coxph(Surv(1:10) ~ rep(4,10)).
}}

\section{Changes in version 2.42-1}{
  \itemize{
    \item Add xtfrm method for Surv objects.
    \item Fix error in logLik.coxph.null (incorrect class)
    \item Fix error in pyears, would fail for a model with no
    predictors and dataframe=TRUE.
    \item tmerge would fail if an id was missing, give a message
    instead
    \item Stronger date checks in survexp, i.e., that the column
    of a data frame is a date if and only if the matching ratetable
    dimension is a date.
    \item Restore the order of the elements of coxph objects; as some
    other packages depend on both the names and the order.  It had been
    modified when the residual argument was added to coxph.fit.
    \item Add a more rigorous check for overflow in the coxph iteration:
    M Tsagris supplied an edge case example where the information matrix
    fails one iteration before anything else.  
}}

    
\section{Changes in version 2.42-0}{
  \itemize{
    \item Fix a bug in the agfit4.c routine, based on data sets from Ivo
    Sousa Ferreira and Marloes Derks.  This was introduced in 2.39-1 and
    leads to incorrect solutions for selected data sets.  Such data sets
    are a rare edge case, however.  In detail:
    In a start stop data set with strata assume two adjacent event times
    in one stratum of d1 and d2, say, and a set of k censored intervals
    (a,b) also in that stratum such that a>=d1 and b<d2.  (Such intervals are
    never at risk for an event and could be elminated from the data set
    without loss.) If k >= the number of intervals that overlap both d1
    and d2, and in the prior stratum the smallest time was an event,
    some variables that track who is in the risk set got out of sync,
    and contributions to the loglik, first and second derivative at d1
    would be incorrect.  I expect such data sets are extremely rare.
    However, the survSplit routine and mstate packages can generate data
    sets with a LOT of the unneeded intervals.  (The data set in
    question came from mstate.)

    \item Use format.pval() and printCoefmat in more of the print
    functions.  This aligns the format with that of base R.

    \item Update the vcov function to accept the new complete= argument.
    \item Update statefig to accept vectors of colors.

    \item The [.survfit routine would complain on the use of fit[1]
    when fit contained a single curve.  This is now legal.
    \item Change NAMED() to MAYBE_REFERENCED() at the suggestion of R
    core

    \item Add the yates() routine for population prediction,
    and accompanying vignette.
    \item Update the survival rate tables (survexp.mn, survexp.us,
    survexp.usr), to add data for more calendar years.

    \item Bow to user pressure: marks now appear on survival curves for
    censoring times that are tied with an event time, plotted at the
    midpoint of the vertical step.  Also, replace the outdated
    \code{mark} option with \code{pch}.
  }
}

\section{Changes in version 2.41-5}{
  \itemize{
    \item Update the survexp.us and survexp.usr rate tables.  They now
    contain years 1940 to 2012.  They however lost the breakdown of the
    first year of life into smaller intervals as the recent US census data
    lacks that information.  Update the code for ratetables: a cutpoint
    attribute vector can now be of class Date, and names(dimnames) can
    supplant the dimid attribute.  (Only creators of rate tables are impacted
    by these last two.)

    \item Change all instances of "1-pchisq(...)" to instead use the
    lower.tail=FALSE argument.
}}

\section{Changes in version 2.41-4}{
  \itemize{
    \item The coxph routine did not check for infinite predictors (these
    are not screened out by na.action), and these could cause the
    iteration to fail.  Added a check and stop() statement.  The example
    was provided by Glenn Tisdale.

    \item When conf.times was used in plot.survfit, the bars were not
    perfectly centered on the target values

    \item Add the residual and concordance argument to coxph.fit and
    agreg.fit, at the request of S Venkat.  These speed up the function
    when a calling routine only needs the partial likelihood.

    \item Fix error in survfit: if timefix=FALSE was specified we forgot
    to set a key variable and the routine fails.  Pointed out by Sarah
    Streett. 8Apr2017.

    \item Change the scale argument of summary.coxph so that it affects
    the coefficient and se(coef), not just the confidence interval.

    \item Fix an error in survfitCI when using the start.time argument, and
    add a test case for it.

    \item Add tail.Surv method per a request from Michael Lawrence.
    Also add duplicated, anyDuplicated, and unique methods.
}}

\section{Changes in version 2.41-3}{
  \itemize{
    \item A check for infinite loglik was incorrect in agfit4.c, and could
    fail to detect the need for step halving.  It required a very
    unusual data set to trigger this.

    \item The survfit routine would fail for interval censored data, on
    a group that had only a single step in the curve.  (Needed to add
    drop=FALSE to a matrix subscript.)

    \item Minor change to Surv to ensure that its check for difftime
    objects will not trigger a "length >1 inside an if ()" warning.

    \item The summary.survfit function had n.censor wrong when there
    were multiple curves and censor=TRUE (spurious NA values).  Added more
    lines to the test suite.

    \item Pointed out by Mikko Korpela: the dynamic symbols check added
    in 2.41-0 requires R version 2.16 or later.  Add an ifdef to init.c
    that checks the version of R, mimicking a similar line in the MASS library.
}}

\section{Changes in version 2.41-2}{
  \itemize{
    \item Fix two memory leaks and an uninitialized array, found by B Ripley. 

    \item With Surv(a,b, type='interval2') and a or b infinite, the
    infinite values were incorrectly retained rather then being
    transformed into left or right censoring.  The downstream survfit
    and/or survreg results could then sometimes be in error.

    \item Update cch to correctly deal with nearly tied times, in line
     with the many changes in version 2.40.

     \item Update the README.md file, for github users who didn't read
    noweb/Readme and then get R CMD build errors.
  }
}
\section{Changes in version 2.41-0}{
  \itemize{
    \item Per request if the R-core, add R_useDynamicSymbols(dll,FALSE)
      to the initialization.  This prevents .Call from accessing the
      library when its first argument is a character string.  The reason
      is to stop accidental linking to the routines.
    \item Fix a bug in tmerge, if data2 was not sorted by time within id
      then a tdc(time, x) call's outcomte was incorrect.  Add the ability
      to use a factor as the second variable in a tdc call, and add the
      tdcstart option.
    \item Expose the aeqSurv routine, which is used rectify tied
     time issues.
     \item The survfit routines now save the start.time option (if used) in
     the output object.  This is then used as a default starting point for
     the x-axis in any plots.
     \item Allow survfit.matrix to use different p0 values for different
     curves.
     \item Add type="survival" to predict.coxph
 }}
 
\section{Changes in version 2.40-2}{
  \itemize{
    \item Fix an error in the finegray routine: with strata() the
    resulting data sets could have incorrect status values.  Pointed out
    by Mark Donoghoe.  Added a strata test to tests/finegray.R.  

    \item Remove many "is.R" and "oldClass" calls (vestiges of Splus).
    \item The summary.pyears routine now prints pandoc style tables.
    \item Fix multiple spelling errors in the Rd files; contributed by
    Luca Braglia.
    \item For a multi-state curve, the cumhaz component accidentally had
    the final state removed.  All values were correct, simply an
    overzealous trimming of the final result.

    \item Add a short vignette describing the issue with round off error
    and tied survival times.

    \item Errors in survSplit: a factor status was not propogated, and a
    missing time gave a spurious error message.
}}

\section{Changes in version 2.40-1}{
  \itemize{
    \item For multi-state survival with a big data set and the
    influence=TRUE option, the resulting object could be so long that it
    overflowed an integer counter in the C code.  Add a check in the R
    code and a caution in the help file.
  }
}
\section{Changes in version 2.40-0}{
  \itemize{
    \item Code changes to avoid the new warnings for multiplication of a
    vector * (1 by 1 matrix). 
    
    \item Add a more thorough test case for multi-state survival:
    not all subjects start in the same state, delayed entry, and
    case weights that change within a subject.  This uncovered some
    errors.  More carefully document the influence option.
    
    \item Consistently deal with "almost tied" survival times in the survfit and
    coxph routines.  Uses the same rule and tolerance as the all.equal
    function to declare two time value equal.  The issue arises due to
    round off errors, e.g., from cacluations using days/365.25.
    
    \item Add the statefig function and a multi-state vignette.

    \item The rsurvreg function was not exported.  NAMESPACE fix.

    \item Fix some labeling errors in the graphs for the adjusted
    survival curves vignette (consequences of the xscale change in
    2.38-5).

    \item Update multi-state survival so that the robust (default)
    variance for a weighted data set treats these as sampling weights
    rather than case weights.  This makes it consistent with the
    behavior of coxph.  (Multiplication of all the weights by a constant
    now leaves the variance unchanged.) (9/2016)

    \item Surv(time, status) would fail when status was a factor with
    only two levels.  This was due to an assumption that no user would
    ever want this, i.e., ever do it on purpose, and so it must be a mistake
    which should be caught.  This was a bad assumption.

    \item Add the start.time argument to survfit.coxph. 10Sep2017
}}
\section{Changes in version 2.39-5}{
  \itemize{
    \item The summary.survfit routine assumed that the times argument
    was sorted, contrary to the documentation.  Pointed out by Torsten
    Hothorn.
    \item The tmerge function would fail if the time variable was a Date
      object.  It was due to the fact that as.Date(as.numeric(x)) 
      fails when x is a date.  (A design flaw in Date, IMHO).  There were
      also flaws when both the first and second data set were not sorted
      by id; added a more complete test case for this.

    \item An earlier change in dim.survfit had felled the survfit.matrix
    function: it incorrectly assumed strata when there were none.
    Unfortunately this didn't generate an error but rather multiple
    copies of a single curve (and an incomprehensible explanation of
    this single curve in the vignette).  Pointed out by E Lundt.

    \item print.summary.survfitms would complain if only a single time
    was returned.  A case where drop=FALSE was needed.

    \item Add a test for survSplit to ensure that it works with both the
    formula based and old interface.  Add documention on
    how variable names are chosen to the help file.

    \item Error in subscripting survival curves: if fit was a survfit
    curve from left-truncated data, fit[k] had an incorrect n.enter
    component.  (An old error, which shows how rarely that component is
    used.)  Pointed out by Beth Atkinson.

    \item Remove n.enter from the default printout of summary.survfit,
    to make the printout more compact.
    It remains in the summary object but was very rarely used.
    \item Update the points.survfit function to handle multiple colors
    and/or plotting characters.  If a survfit object has multiple curves
    we cycle through these in the same manner as matpoints would.
    
}}

\section{Changes in version 2.39-4}{
  \itemize{
    \item Create a stronger test suite for summary.survfit, and use
    it to actually fix the error that 2.39-3 claimed to fix.  This
    uncovered a long-standing inaccuracy with n.risk for in-between
    time points.
    \item Add a section on monotone splines to the splines vignette.
}}
  
\section{Changes in version 2.39-3}{
  \itemize{
    \item For multi-state curves, the returned n.event component lost
    its dimensions if any of the curves had only one observation.

    \item Fix error in summary.survreg.  For multiple curves and
    requested time points at or before the first time point in the data,
    the values from curve 1 was used for all.  Pointed out by T Eigentler.

    \item Fix an unitialized variable in C code, pointed out by Brian Ripley.
}}

\section{Changes in version 2.39-2}{
  \itemize{
    \item Small updates based on feedback from CRAN
}}

\section{Changes in version 2.39-1}{
  \itemize{
    \item Label the output dimnames from pyears with the variable names
    from the model.  This makes it easier to read.
    
    \item Replace any refrences to model.frame with "stats::model.frame"
    (all 38 of them).  The model.frame function uses non-standard
    evaluation rules, and holding its hand like this is the only way to
    ensure that we don't call a user function of the same name.
    
    \item The Surv function would almost always label the columns of the
    resulting matrix, and the glmnet function depended on this. It now
    always labels them per a request from Trevor Hastie.

    \item Add the finegray function and expand the competing risks
    vignette to document it.

    \item Add a check to the quantile.survfit function for multi-state
    models; quantiles are not well defined for this case.

    \item Changes to the iteration path and convergence tests for coxph
    models with (start, stop] data, driven by two user examples that
    failed.  The data sets had serious statistical issues of
    collinearity and/or outliers such that the final fits are not
    practically useful, but now the routine finishes gracefully instead
    of dying.  The upshot is much more care about the order in which
    additions and subtractions of large numbers are done so as to avoid
    cancellation error.

    \item Fix an error to summary.survfit with the times argument: for
    intermediate time points it would sometimes choose the wrong value
    for the number at risk.  (Number at risk is a left continuous
    function.) 
}}
    
\section{Changes in version 2.38-5}{
  \itemize{
    \item Add more graphical arguments to plot.cox.zph in response to a user
    request.
    
    \item Remove some of last vestiges of Splus support from the header
    files for the C code, per a request from R core to remove mention of S.h.
    
    \item Multiple updates and corrections to the tmerge function,
    including improvements to the vignette.  (As a result of using it in
    a class where the TA tried out all manner of combinations.)
    
    \item Update survSplit: it now handles all types of status variables
    (0/1, TRUE/FALSE, factors), the id and episode arguments are useful
    for start/stop data, the data retains its original sort order (new
    observations are inserted rather than put at the end), and the
    function is illustrated in a vignette.
    
    \item Add the conf.times argument to plot.survfit.  This
    allows for confidence bars at specified times, which are useful
    when the plot is crowded.

    \item Survfit changes that are NOT backward compatable!
    \itemize{
      \item Change the default for mark.time to FALSE
      \item Change the behavior of xscale so that it matches that of
      yscale, i.e., it changes only the label and not the underlying
      scale.  Follow on annotations such as legend or locator are in the
      orignal scale of the data.
      \item For a matrix of curves, e.g. competing risks, print and
      plot them in column major order rather than row major, so as 
      to match the usual R behavior.
      }
    
    \item Fix an error in the help page for the cohort
    argument of survexp, pointed out by Karl Ove Hufthammer.

    \item The anova and logLik functions would fail when given a
    null model (right hand side of 1 or only an offset).  Pointed
    out by Karl Ove Hufthammer.

    \item The recently added code to generate an error when the same
    variable appears on both sides of a formula in coxph (a good idea)
    caused a failure if there was offset statement that contains a '-'
    sign.  Pointed out by Abra Jeffers.
}}

\section{Changes in version 2.38-3}{
  \itemize{
    \item Add more imports to the NAMESPACE file per a request from CRAN

    \item Add a length method for Surv objects.  Requested by Max Kuhn.
    (2015/6/17).

    \item Fix an error in neardate. When both input data sets were
    unsorted the last match could be wrong.
}}

\section{Changes in version 2.38-2}{
  \itemize{
    \item Change print.coxph to use the printCoefmat routine, which l
    leads to nicer p-values.  Other print routines will follow unless
    there is an outcry.  (But I forced signif.stars=FALSE: my tolerance of
    bad practice has limits.)
    
    \item Make those parts of the competing risks vignette which depend
    on the cmprsk library conditional.  Otherwise the build fails for
    those without the pacakge.
    
    \item The coxph function could fail converge for a set of very collinear
    predictors when using (start, stop) data; revealed in a test case
    sent by G Borstrom.  This was due to deficiency in a check for
    near infinite coefficients, which had already been updated for some
    but not all cases.  (2015/6/3)
    
    \item Update anova.coxph to use the model.frame.coxph function; the 
    current code had scoping errors if embedded in a function.  Add an
    anova.coxph.penal function to correctly handle models with pspline
    terms.

    \item Fix an error in the tmerge function.  Using the options
    argument would generate a spurious error.
    \item Pyears could fail on very long formulas due to a deparse() issue.
    
    \item Add the number of observations used and deleted due to missing
    to summary.pyears.
    
    \item Allow the combination of a null coxph model (~1 on the right)
    and the exact calculation for tied times.  No one had ever asked for
    this before.  (2015/3/25)
    
    \item Shorten the default printout for survfit. The records, n.max
    and n.start columns are often the same: if so suppress duplicates.
    
    \item Move the anova.coxphlist function from the survival package to
    coxme.  (2015/3/3)

    \item Change the logLik method for coxph models so that the nobs
    component is the number of events rather than the number of rows in
    the data.  This is superior for follow on methods such as AIC.

    \item Add a test to the coxexact.c routine for too large a data set;
    too many tied times could lead to integer overflow.  "Fixing" the error
    is not sensible: the computation for such a data set would take decades.
    Add some more explanation to the help pages as well.
}}

\section{Changes in version 2.38-1}{
  \itemize{
    \item Fix an error discovered by CRAN, which triggered a core dump
    for them on a particular manual page (but never for me).  The linear
    predictors from a frailty model contained NA values (incorrect),
    leading to failure in survConcordance.fit. (2015/2/16).
    
    \item An error was found in the mgus data set (a progression after
    death).  Now corrected, and added a little more follow-up time for
    some subjects.
    
    \item Add error check for infitinte weights or offsets.  This in respose
    to a bug report where someone did this on purpose, trying to mimic
    cure fractions, and then found that survfit.coxph failed.

    \item Robust variance is not supported for a coxph model with the
    "exact" approximation.  (Rarely requested and a lot of work to add.)
    Add an error message to clogit(), so users get a more useful notice of
    the issue rather than a late error from residuals.coxph.
    
    \item Update the rats data set: it now includes both female and male
    litters so as to match the documentation.
    
    \item The term frailty(x) would fail if x were a factor, and not all
    levels were present.  Pointed out by Theodor Balan.
    
    \item Fix error of "abs" instead of "fabs" in the agfit4.c code;
    pointed out to me by CRAN.
    
    \item Replace all instances of the obsolete prmatrix function.
    
    \item Modify pyears to allow cbind(time, count) as the response,
    giving a cumulative sum of counts, when the counts per observation
    may be other than 0/1.
    
    \item The lines.survfit function was incorrect for data sets that
    used the start.time option and xscale (it neglected to rescale the
    start time.)

    \item An increasingly common error is for user to put the time
    variable on both sides of a coxph equation in the mistaken belief
    that this is a way to create time-dependent coefficients.  Generate
    a warning message for this case.
    
    \item Update the basehaz function to a simple alias for "survfit".
    Prior versions called surfit but then only returned part of the
    object.  Update 2/2015: reverted the change.  It turns out that 6
    different packages that depend on survival also depended on the
    old behavior.  
    
    \item Make the default value for the shortlabel argument of strata()
    more nuanced.  If the argument is a single factor, assume that we
    don't need to prepend the variable name to its levels.
    
    \item Return the weights vector, if present, as part of the survreg
    object.
    
    \item For interval censored points and the symmetric distributions
    (Gaussian and logistic) response type residuals were incorrect.
    Silly error: needed (x-mean)/scale not x/scale - mean.

    \item Martingale residuals could be incorrect for the case of model with
    (start, stop] data and a pspline term.  Refactor the code so that
    all of the possible code paths call the same C routine to do the residuals.
    Add a new test for this case, and further tests to verify that
    predict(type='expected') and residuals agree.
        
    \item Fix bug pointed out by D Dunker: if a model had both tt() and
    cluster() terms it would fail with a length error.
    
    \item Fix a rare bug in plot.survfit: if a multistate curve rose and
    then later fell to exactly the same value, the line would be
    incorrect.
    
    \item Add calls to the R_CheckUserInterrupt to several routines, so
    that long calculations can be interrupted by the user.

    \item The anova.coxph function would fail if the original call had a
    subset argument. Pointed out by R Fisher.   11May2014
}}
    
\section{Changes in version 2.37-7}{
  \itemize{
    \item Remove a dependency on the survey package from the adjusted
    survival curves vignette, at the request of CRAN.  (The base +
    required bundle needs to be capable of a stand-alone build.)
    
    \item Fix error in calcuation of the y-axis range for survival curve
    plots whenever the "fun" argument could produce infinite values,
    e.g., complimentary log-log plots transform 1 to -Inf.  Pointed out
    by Eva Boj del Val.  (Add finite=TRUE to range() call).
}}

\section{Changes in version 2.37-6}{
  \itemize{
    \item The plot for competing risk curves could have a spurious
    segment.  (Found within 3 hours of submitting 2.37-5 to CRAN.)

    \item The lines method for survexp objects was defaulting to a
    step function, restore the documented default of a connected
    line.
    \item Add a levels method for tcut objects. 14Jan2014
  }
}  
\section{Changes in version 2.37-5}{
  \itemize{
    \item Add vignette on adjusted survival curves.
    \item Add vignette concerning "type 3" tests.
    
    \item Make the tt() function invisible outside of a coxph formula.
    There was a complaint about conflicts with another package, and
    there is not really a good reason to have it be a global name.
    An R-devel discussion just over 1 year ago showed how to accomplish this.
   
    \item The modeling routines are set in two parts, e.g., coxph sets
    up the model and coxph.fit does the work.  Export more of the ".fit"
    routines to make it easier for other packages to build on top of
    this one.
    
    \item Updates to the model.matrix and model.frame logic for
    coxph.  A note from F Harrell showed that I was not correctly
    dealing with the "assign" attribute when there are strata * factor
    interactions.  This led to cleanup in other cases that I had missed
    but which never had proven fatal.  Also added support for tt() terms
    to the stand alone model.matrix and model.frame functions.
    (Residuals for tt models are still not available, but this was a
    necessary first step to that end.) 26Dec13
    
    \item The Surv function now remembers attributes of the input
    variables that were passed to it; they are saved as
    "inputAttributes".  This allows the rms package, for instance, to
    retain labels and units through the call.
    
    \item Update summary.coxph.penal to produce an object, which in turn
    has a print method, i.e., make it a "standard" summary function.
    
    \item Add a logLik method for coxph and survfit objects.
    
    \item Allow for Inf as the end of the time interval, for interval
    censored data in the Surv function.
    
    \item The predict.coxph function would fail if it had both a newdata
    and a collapse argument.  Pointed out by Julian Bothe.  25Sep13
    
    \item Survexp can now produce expecteds based on a stratified Cox
    model.  Add the 'individual.s' and 'individual.h' options to return
    indivudual survival and cumulative hazard estimates, respectively.
    The result of survfit now (sometimes) includes the cumulative
    hazard.  This will be expanded. 29Jul13
    
2    \item Change code in the coxpenal.fit routine: the use of a vector of
    symbols as arguments to my .C calls was confusing to a new CRAN
    consistency check.  Both the old and new are legal R; but the old
    was admittedly an unusual construction and it was simpler to change it.
    
    \item Fix a bug in survfit.coxph pointed out by Chris Andrews, whose
    root cause was incorrect curve labels when the id option is used. 27Jun13
    
    \item Add rsurvreg routine.
    
    \item Change survfit.coxph routine so that it detects whether
    newdata contains or does not contain strata variables, and acts
    accordingly. If newdata does containe strata then  the output will
    contain only those data-value and strata combinations specified by the
    user. Retain strata levels in the coxph routine for use
    in the survfit routine, to correctly reconstruct strata levels.
    Warn about curves with interactions.  18Ju13

    \item Add a dim method for survival curves.
    
    \item For competing risks curves that use the istate option, the
    plotted curves now start with the correct (initial) prevalence of
    each state.  22May13
    
    \item The survreg function failed with the "robust=T"
    option. Pointed out by Jon Peck.  Test case added.  6May13
    
    \item Kazuki Yoshida pointed out that rep() had no method for Surv
    objects.  This caused the survSplit routine to fail if the data
    frame contained a Surv object.  3May13
    
    \item Per a request from Milan Bouchet-Valet fix an issue in survfit
    that arose when the OutDec option is set to ',': it did not
    correctly convert times back from character to numeric.

    \item The plot.survfit function now obeys "cex" for the size of the
      marks used for censored observations.
}}

\section{Changes in version 2.37-4}{
  \itemize{
    \item Subscripting error in predict.coxph for type=expected, se=T,
    strata in the model, newdata, and multiple strata in the new data
    set.  Pointed out by Chris Andrews.  The test program has been
    tweaked to include multiple strata in newdata.
}}
    

\section{Changes in version 2.37-3}{
  \itemize{
    \item Minor flaw in [.survfit.  If "fit" had multiple curves, and
    fit$surv was a matrix, and one of those curves had only a single observation
    time, fit[i,] would collapse columns when "i" selected that curve,
    though it shouldn't.  

    \item Changed all of the .C and .Call statements to make use of
    "registered native routines", per R-core request. Add file src/init.c 

    \item Error in plot.survfit pointed out by K Hoggart -- the "+"
    signs for censored observations were printing one survival time to
    the left of the proper spot.  Eik Vettorazi found another error if
    mark.time is a vector of numerics.  These are the results of merging
    the code for plot, lines and points due to some discrepancies between
    them, plus not having any graphical checks in the test suite.
    
    \item Repair an error in using double subscripts for the survfitms
    objects.
    
    \item Add the US population data set, with yearly totals by age and sex 
    for 2000 onward.  It is named uspop2, since there is already a "uspop" 
    data set containing decennial totals from 1790 to 1970.
    
    \item Not all combinations of strata Y/N and CI Y/N worked in the
    quantile.survfit function, pointed out by Daniel Wallschlaeger
    (missing a function argument in one if-else combination).
    Added a new test routine that verifies all paths.

    \item The first example in predict.survreg help file needed to have
    \code{I(age^2)} instead of \code{age^2} in the model: R ignores the
    second form. (I'm almost sure this worked at one time, perhaps in Splus).
    It also needed different plot symbols to actually match the
    referenced figure.  Pointed out by Evan Newell.

    \item Fix a long-standing problem with cch pointed out by Ornulf Borgan
    leading to incorrect standard errors.  A check in the underlying
    coxph routines to deal with out of bounds exponents, added in
    version 2.36-6, interacted badly with the -100 offset used in cch.
    It only affected models using (start, stop) survival times. 
}}

\section{Changes in version 2.37-2}{
  \itemize{
    \item Two bugs were turned up by running tests for all the
    packages that depend on survival (158 of them).
}}
\section{Changes in version 2.37-1}{
  \itemize{
    \item Add a new multi-state type to the Surv object.  Update the
    survfit routine to work with it.  The major change is addition
    of a proper variance for this case.
    More functionality is planned.
    
    \item Remove the fr_colon.R test program.  It tests an ability that
    has been superseded by coxme, on a numerically touchy data set, and
    it was slow besides.  For several other tests that produce warning
    messages and are supposed to produce said messages, add extra
    comments to that effect so testers will know it is expected.
    
    \item The code has had several "if.R" clauses to accomodate Splus vs
    R differences, which are mostly class vs oldClass.  These are now being
    removed as I encounter them; since our institution no longer uses
    Splus I can no longer test the clauses' validity.
    
    \item The fast subsets routine coxexact.fit incorrectly returned the
    linear predictor vector in the (internal) sorted order rather than
    data set order.  Pointed out by Tatsuki Koyama, affecting the result
    of a clogit call.  6Nov2012
    
    \item Jason Law pointed out that the sample data set "rats" is from
    the paper by Mantel et.al, but the documentation was for a data
    set from Gail, Santner and Brown.  Added the Gail data as rats2 and
    fixed the documentation for rats.
    
    \item For predict.coxph with type="terms", use "sample" as the
    default value for the reference option.  For all others the default
    remains "strata", the current value.  Type terms are nearly always passed
    forward for further manipulation and per strata centering can mess
    things up: termplot() for instance will no longer show a smooth
    function if the results are recentered within strata.
        
    \item Fix bug in summary.aareg, which was unhappy (without cause) if
    the maxtime option was used for a fit that did not include the
    dfbeta option.  Pointed out by Asa Johannesen.
    
    \item The coxph fitting functions would report an error for a null model
      (no X variables) if init was specified as numeric(0) rather than NULL.
    
    \item Update the description and citation files to use the new
    "person" function described in the R Journal.  Also add the
    ByteCompile directive per suggestion of R core.

    \item Allow an ordinary vector as the left hand side of survConcordance.

    \item Update anova.coxphlist to reject models with a robust variance.
 
    \item The survfit function had an undocumented backwards-compatability 
    that allows the newdata argument to be a vector with no names.  An
    example from Damon Krstajic showed that this does not work when the
    original model has a matrix in the formula.  Removed the feature.
    (This is for survfit.coxph.)  Also clarified the code and its 
    documentation about what is found where -- environments, formulas,
    and the arguments of eval, which fixes a problem pointed out by xxx
    where the result of a Surv call is used in the coxph formula.

    \item Fix an issue in summary.survfit pointed out by Frank Harrell.  The
    strata variable for the output always had its labels in sorted order,
    even when a factor creating the survival curves was otherwise.  (This was
    due to a call to factor() in the code.)  The print routine would then
    list curves in sorted order, which might well be contrary to the user's
    wishes.  The curves were numerically correct.

    \item Add the anova.coxmelist function to the namespace so that it is
    visible.  If someone has a list of models the first of which was
    a coxph fit and the list includes coxme fits, then anova.coxph will
    be the function called by R, and it will call anova.coxmelist.

    \item Fix a bug pointed out by Yi Zhang and Mickael Hartweg.
    If a coxph model used an offset, then a predicted survival curve
    that used newdata (and the offset variable of course) would be
    wrong, e.g. survival values > 1.
    A simple misplaced parenthesis was the cause.
    A recent paper by Langholz shows how to get absolute survival from
    case-control data using an offset, which seems to have suddenly made this
    feature popular.

    \item Per further interaction with Yi Zhang, a few items were
    missing from the S3methods in the NAMESPACE file: as.matrix.Surv,
    model.matrix.coxph, model.matrix.survreg, model.frame.survreg.
}}

\section{Changes in version 2.36-14}{
  \itemize{
    \item A supposedly cosmetic change to coxph in the last release
	caused formulas with a "." on the right hand side to fail.  Fix this
	and add a case with "." to the test suite.
      }
    }

\section{Changes in version 2.36-13}{
  \itemize{
    \item Add the anova.coxmelist function.  This is in the survival
    package rather than in coxme since "anova(fit1, fit2)" is valid when
    fit1 is a coxph and fit2 a coxme object, a case which will cause this
    function to be called by way of anova.coxph.
    
    \item More work on "predvars" handling for the pspline function,
    when used in predict calls.  Add a new test of this to the suite,
    and the makepredictcall method to the namespace.
    Fixes a bug pointed out by C Crowson.  

    \item Deprecate the "robust" option of coxph.  When there are
    multiple observations per subject it is almost surely the wrong
    thing to do, while adding a "cluster(id)" term does the correct
    thing. When there is only one obs per subject both methods work
    correctly.

    \item Add documentation of the output structure to the aareg help
    file.

    \item Change ratetableDate so that it still allows use of chron
    objects, but doesn't need the chron library.  This eliminates a
    warning messge from the package checks, but is also a reasonable
    support strategy for a moribund package.  (Some of the local users keep
    datasets for a long long time.)

    \item Fix a bug in summary.survfit for a multiple-strata survival
    object.  If one of the curves had no data after application of the
    times argument, an output label was the wrong length.
    
    \item Fix a bug pointed out by Charles Berry: predict for a Cox
    model which has strata, and the strata is a factor with not all its
    levels represented in the data.  I had a mistake in the subscripting
    logic: number of groups is not equal to max(as.integer(strata)).
    
    \item Changes to avoid overflow in the exponent made in 2.36-6
    caused failure for one special usage: in case-cohort designs a dummy
    offset of -100 could be added to some observations.  This was being
    rounded away.  The solution is to 1: have coxsafe not truncate small
    exponents and 2: do not recenter user provided offset values.

    \item Fix bug in survfit.coxph.  Due to an indexing error I would
    sometimes create a huge scratch vector midway through the
    calculations (size = max value of "id"); the final result was always
    correct however.  Data set provided by Cindy Crowson which had a
    user id in the billions.

    \item Fix bug pointed out by Nicholas Horton: predictions of
    type expected, with newdata, from a Cox model without a strata
    statement would fail with "x not found".  A misplaced parenthesis
    from an earlier update caused it to not recreate the X matrix even
    though it was needed later.  Also add some further information to
    the predict manual page to clarify an issue with frailty terms.
    }}

\section{Changes in version 2.36-12}{
  \itemize{
    \item Fix a bug in the new fast subsets code.  The test suite had no
    examples of strata + lots of tied times, so of course that's the
    case where I had an indexing error.  Add a test case using the
    clogit function, which exercises this.

    \item Further memory tuning for survexp.
    }}

    \section{Changes in version 2.36-11}{
  \itemize{
    \item Make survexp more efficient.  The X matrix was being modified
    in several places, leading to multiple copies of the data.  When the
    data set was large this would lead to a memory shortage.

    \item Cause anova.coxph to call anova.coxme when a list of models
    has both coxph and coxme objects.

    \item Add the quantile.survfit function.  This allows a user to
    extract arbitrary quantiles from a fitted curve (and std err).

    \item Fix an error in predict.coxph.  When the model had a strata
    and the newdata and reference="sample" arguments were used, it
    would (incorrectly) ask for a strata variable in the new data set.

    \item Incorporate the fast subsets algorithm of Gail et al, when 
    using coxph with the "exact" option.  The speed increase is profound 
    though at the cost of some memory.    Reflect this in the
    documentation for the clogit routine.
    Note that the fast computation is not yet implemented for
    (start,stop) coxph models.

    \item Change the C routine used by coxph.fit from .C to .Call
    semantics to improve memory efficiency, in particular fewer copies
    of the X matrix.

    \item Add scaling to the above routine.  This was prompted by a user
    who had some variables with a 0-1 range and others that were
    0 - 10^7, resulting in 0 digits of accuracy in the variance matrix.
    (Economics data).

    \item Comment out some code sections that are specific to Splus.
    This reduced the number of "function not found" warnings from R CMD check.
}}

\section{Changes in version 2.36-10}{
  \itemize{
    \item 30 Sept 2011: The na.action argument was being ignored in
    predict.coxph; pointed out by Cindy Crowson.

    \item The log-likelihood for survreg was incorrect when there are
    case weights in the model.  The error is a fixed constant for any
    given data set, so had no impact on tests or inferences.  The error
    and correction were pointed out by Robert Kusher.
    
    \item A variable name was incorrect in survpenal.fit.  This was in a
    program path that had never been traversed until Carina Salt used
    survreg with a psline(..., method='aic') call, leading to a
    "variable not found" message.

    \item Punctuation error in psline made it impossible for a user to
    specify the boundary.knots argument.  Pointed out by Brandon
    Stewart.

    \item Add an "id" variable to the output of survobrien.

    \item The survfitCI routine would fail for a curve with only one
    jump point (a matrix collapsed into a vector).

    \item Fix an error in survfit.coxph when the coxph model has both a
    strata by covariate interaction and a cluster statement.  The
    cluster term was not dropped from the Terms object as it should have
    been, led to a spurious "variable not found" error.   Pointed out
    by Eva Bouguen.

    \item If a coxph model with penalized terms (frailty, pspline) also
    had a redundant covariate, the linear predictor would be returned as
    NA.  Pointed out by Pavel Krivitsky.
}}

\section{Changes in version 2.36-9}{
  \itemize{
    \item Due to a mistake in my script that submits to CRAN, the fix in
    2.36-8 below was actually not propogated to the CRAN submission.

    \item Fix an error in the Cauchy example found in the survreg.distributions
    help page, pointed out by James Price.

    \item Update the coxph.getdata routine to use the model.frame.coxph
    and model.matrix.coxph methods.

    \item Add the concordance statistic to the printout for penalized models.
}}

\section{Changes in version 2.36-8}{
  \itemize{
    \item Unitialized variable in calcuation of the variance of the
    concordance.  Found on platform cross-checking by Brian Ripley.
    \item Changed testci to use a fixed file of results from cmprsk
    rather than invoking that package on-the-fly.  Suggested by the CRAN
    maintainers.
  }
  }
\section{Changes in version 2.36-7}{
  \itemize{
    \item Due to changes in R 2.13 default printout, the results of many of
    the test programs change in trivial way (one more or fewer digits).
    Update the necessary test/___.Rout.save files.  Per the core team's
    suggestion the dependency for the package is marked as >=2.13.
  }}
  
\section{Changes in version 2.36-6}{
  \itemize{
    \item An example from A Drummond caused iteration failure in
    coxph: x=c(1,1,1,0,1, rep(0,35)), time=1:40, status=1.  The first
    iteration overshoots the solution and lands on an almost perfectly
    linear part of the loglik surface, which made the second iteration
    go to a huge number and exp() overflows.  A sanity check routine
    coxsafe is now invoked on all values of the linear predictor.
    
    \item 1 April: Fix minor bug in survfit.  For left censored data
    where all the left censored are on the very left, it would give a
    spurious warning message when trying to create a 0 row matrix that
    it didn't need or use.  Pointed out by Steve Su.
    
    \item 31 March 2011: One of the plots in the r_sas test was wrong
    (it's been a long time since I visually checked these).  The error
    was in predict.survreg; it had not taken into account a change in
    R2.7.1: the intercept attribute is reset to 1 whenever one
    subscripts a terms object, leading to incorrect results for a model
    with "-1" in the formula and a strata(): the intercept returned
    when removing the strata.  I used this opportunity to move most of
    the logic into model.frame.survreg and model.matrix.survreg
    functions.  Small change to the model.frame.coxph and
    model.matrix.coxph functions due to a better understanding of
    xlevels processing.
    
    \item Round off error issue in survfit: it used both unique(time)
    and table(time), and the resulting number of unique values is not
    guarranteed to be the same for times that differ by a tiny amount.
    Now times are coverted to a factor first.  Peter Savicky from the R
    core team provided a nice discussion of the issue and helped me
    clarify how best to deal with it.  The prior fix of first rounding
    to 15 digits was good enough for almost every data set -- except the
    one found by a local user just last week.
    
    \item Round off error in print.survfit pointed out by Micheal Faye.
    If a survival value was .5 in truth, but .5- eps due to round off
    the printed median was wrong. But it was ok for .5+eps. Simple
    if-then logic error.
    
    \item Re-fix a bug in survfit.  It uses both unique and table in
    various places, which do not round the same; I had added a
    pre-rounding step to the code.  A data set from Fan Chun showed that
    I didn't round quite enough. But the prior rounding did work for a
    time of 2 vs (sqrt(2))^2: this bug is very hard to produce.  I now
    use as.numeric(as.character(factor(x))), which induces exactly the
    same rounding as table, since it is the same compuation path.

    \item Further changes to pspline.  The new Boundary.knots argument
    allows a user to set the boundary knots inside the range of data.
    Code for extrapolation outside that range was needed,
    essentially a copy of the code found in ns() for the same issue.
    Also added a psplineinverse function, which may be useful with
    certain tt() calls in coxph.
    
    \item 10 Mar 2011: Add the capablilty for time-dependent
    transformations to coxph, along with a small vignette describing use
    of the feature.  This code is still incompletely incorporated in
    that the models work but other methods (residuals, predict, etc) are
    not yet defined.
    
    \item 8 Mar 2011: Expand the survConcordance function.  The function
    now correctly handles strata and  time dependent covariates, and
    computes a standard error for the estimate.  All computation is based
    on a balanced binary tree strucure, which leads to computation in
    \eqn{O(n \log_2(n))}{O(n log(n))} time.
    The \code{coxph} function now adds concordance to its output, and
    \code{summary.coxph} displays the result.

    \item 8 Mar 2011: Add the "reference" option to predict.coxph, a
    feature and need pointed out by Stephen Bond.

    \item 4 Mar 2011: Add a makepredictcall method for pspline(), which
    in turn required addition of a Boundary.knots argument to the
    function.
    
    \item 25 Feb 2011: Bug in pyears pointed out by Norm Phillips.  If a
    subject started out with "off table" time, their age was not
    incremented by that amount as they moved forward to the next "in
    table" cell of the result.  This could lead to using the wrong
    expected rate from the rate table.
  }
}

\section{Changes in version 2.36-5}{
  \itemize{
    \item 20 Feb 2011: Update survConcordance to correctly handle case
    weights, time dependent covariates, and strata.

    \item 18 Feb 2011: Bug in predict.coxph found by a user (1 day after
    36-4!).  If the coxph call had a subset and predict used newdata,
    the subset clause was "remembered" in the newdata construction,
    which is not appropriate.
}}

\section{Changes in version 2.36-4}{
\itemize{
  \item 17 Feb 2011: Fix to predict.coxph.  A small typo that only was
  exercised if the coxph model had x=T.  Discovered via induced error in
  the rankhazard package.  Added lines to the test suite to test for
  this in the future.

  \item Removed some files from test and src that are no longer needed.

  \item Update the configure script per suggestion from Kurt H.
  }}
\section{Changes in version 2.36-3}{
  \itemize{

    \item 13 Feb 2011: Add the rmap argument to pyears, as was done for
    survexp, and update the manual pages and examples. Fix one last bug
    in predict.coxph (na.action use).  Passes all the
    tests for inclusion on the next R release.

    \item 8 Feb 2011: Change the name of the new survfit.coxph.fit routine to
     survfitcoxph.fit; R was mistaking it for a survfit method.  Fix
     errors in predict.coxph when there is a newdata argument, including
     adding yet another test program.

   \item 1 Feb 2011: Fix bugs in coxph and survreg pointed out by Heinz
    Tuechler and dtdenes@cogpsyphy.hu, independently, that were the same
    wrong line in both programs.  With interactions, a non-penalized
    term could be marked as penalized due to a mismatched vector length,
    leading to a spurious error message later in the code.
  
  \item 1 Feb 2011: Update survfit.coxph to handle the case of a strata by
    covariate interaction.  All prior releases of the code did this
    wrong, but it is a very rare case (found by Frank Harrell).  Added a
    new test routine coxsurv4.  Also found a bug in [.survfit; for a
    curve with both strata and multiple columns, as produced by
    survfit.coxph, it could drop the n.censored item when subscripting.
    A minor issue was fixed in coxph: when iter=0 the output coefficient
    vector should be equal to the input even when the variance is
    singular. 

  \item 30 Jan 2011: Move the noweb files to a top level directory, out of
    inst/.  They don't need to be copied to binary installs.
    
  \item 22 Jan 2011: Convert the Changelog files to the new inst/NEWS.Rd
    format.
  
  \item 1 Jan 202011: The match.ratetable would fail when passed a data
    frame with a character variable.  This was pointed out by Heinz
    Tuechler, who also did most of the legwork to find it.  It was
    triggered by the first few lines of tests/jasa.R (expect <- ....)
    when options(stringsAsFactors=FALSE) is set. 
 }
}

\section{Changes in version 2.36-2}{
\itemize{
  \item 20 Dec 2010: Add more test cases for survfit.coxph,
    which led to significant updates in the code. 

  \item 18 Nov 2010: Add nevent to the coxph output and printout in
    response to a long standing user request.

  \item 14 Dec 2010: Add an as.matrix method for Surv objects. 

  \item 11 Nov 2010: The prior changes broke 5 packages: the dependencies form a bigger
test suite than mine!  1. Survival curve for a coxph model with sparse
frailty fit; fixed and added a new test case.  2. survexp could fail if 
called from within a function due to a scoping error.  3. "Tsiatis" was once
a valid type (alias for 'aalen')  for survfit.coxph; now removed from the 
documentation but the code needed to be backwards compatable.  The other two
conflicts were fixed in the packages that call survival.  There are still
issues with the rms package which I am working out with Frank H.
 }
}

\section{Changes in version 2.36-1}{
 \itemize{
  \item{27 Oct 2010: Finish corrections and test to the new code. It now passes
the checks.  The predict.coxph routine now does strata and standard errors
correctly, factors propogate through to predictions, and numerous small 
errors are addressed.  Predicted survival curves for a Cox model has been
rewritten in noweb and expanded. Change the version number to 2.36-1.}

  \item{17 Oct 2010: Per a request from Frank Harrell (interaction with his library),
survfit.coxph no longer reconstructs the model frame unless it really needs
it: in some cases the 'x' and 'y' matrices may be sufficient, and may be
saved in the result.  Add an argument "mf" to model.matrix.coxph for more 
efficient interaction when a parent routine has already recovered the model 
frame.
  In general, we are trying to make use of model.matrix.coxph in many of the
routines, so that the logic contained there (remove cluster() calls, pull
out strata, how to handle intercepts) need not be replicated in multiple 
places.}

  \item{12 Oct 2010: Fix a bug in the modified lower limits for survfit (Dory & Korn).
A logical vector was being inadvertently converted to numeric.  Pointed out
by Andy Mugglin.  A new case was added to the test suite. }
 }
}

\section{Changes in version 2.35}{ 
 \itemize{
  \item{15 July 2010: Add a coxph method for the logLik function.  This is used by
the AIC function and was requested by a user.}

  \item{29 July 2010: Fix 2 bugs in pyears.  The check for a US rate table was off
(minor effect on calculations), and there was a call to julian which assumed
that the origin argument could be a vector.  }

  \item{21 July 2010: Fix a problem pointed out by a user: calling survfit with almost
tied times, e.g., c(2, sqrt(2)^2), could lead to an inconsistent result.  Some
parts of the code saw these as 2 unique values per the unique() function, some
as a single value using the results of table().  We now pre-round the input
times to one less decimal digit than the max from .Machine$double.digits.
  Also added the noweb.R processing function from the coxme package, so that
the noweb code can be extracted "on the fly" during installation using
commands in the configure and cleanup scripts.  }

  \item{11 July 2010: A rewrite of the majority of the survfit.coxph code.  The primary
benefits are 1: finally tracked down and eliminated the bug for standard errors
of case weights + Cox survival + Efron method; 2: the individual=TRUE and FALSE
options now use the same underlying code for curves, before there were some
options valid only for one or the other; 3: code was rewritten using noweb 
with a considerable increase in documentation; 4: during the verification
process some errors were found in the test suite and corrected, e.g., a 
typo in my book led to failure of an all.equal test in book4.R.  Similar
to the rewrite for survfit several years ago, the new code has far less use
of .C to help transparency.}

  \item{21 May 2010: Fix bug in summary.survfit.  For a survival curve from a Cox model
with start,stop data, the 'times' argument would generate an error.}

  \item{24 May 2010: Fix an annoyance in summary.survfit.  When the survival data 
had an event or censor at time 0 and summary is called with a times argument,
then my constructed call to approx() would have duplicate x values.  The answer
was always right, but approx has begun to print a bothersome warning message.  
A small change to the constructed argument vector avoids it.}

  \item{7 April 2010: Minor bug pointed out by Fredrik Lundgren.  In survfit if the
method was KM (default) and error = Tsiatis an error message results.  Simple
fix: code went down the wrong branch.}

  \item{24 Feb 2010: Serious bug pointed out by Kevin Buhr.  In Surv(time1, time2,stat)
if there were i) missing values in time1 and/or time2, ii) illegal value
sets with time1 >=time2, and iii) all the instances of ii do not preceed all
the instances of i, then the wrong observation (not the illegal) will be 
thrown out.  Repaired, and a new test added.
  Minor updates to 3 test files: survreg2, testci, ratetable.}

  \item{8 Feb 2010: Bug pointed out by Heinz Tuechler -- if a subscript was dropped from
a rate table the 'type' attribute got dropped, e.g. survexp.usr[,1,,].}

  \item{26 Jan 2010: At the request of Alex Bokov, added the xmax, xscale, and fun
arguments to points.survfit.}

  \item{26 Jan 2010: Fix bug pointed out by Thomas Lumley -- with case weights <1 a Cox 
model with (start, stop) input would inappropriately decide it needed to do
step halving to find a solution, eventually failing to converge.  It was
treating a loglik >0 as an indication of failure, but such values arise for
small case weights. Let L(w) be the loglik for a data set where everyone is
given a weight of w, then L(w)= wL(1) - d log(w) where d=number of deaths in
the data.  For small enough w positivity of L(w) is certain.}

  \item{25 Jan 2010: Fix bug in summary.ratetable pointed out by Heinze Tuechler.  Added
a call to the function to the test suite as well.}

  \item{15 Dec 2009: Two users pointed out a bug that crept into survreg() with a
cluster statement, when a t(x)%*%x was replaced with crossprod.  A trivial
fix, but in response I added another test that more formally checks the
dfbeta residuals and found a major oversight for the case of multiple
strata.  }

  \item{14 Dec 2009: 1.Fix bug in frailty.xxx, if there is a missing value in the levels
it gets counted by "length(unique(x))" (frailty is called before NA
removal.)  2.SurvfitCI had an incorrect CI with case weights, and 3. in
survreg a call to resid instead of residuals.survreg, before the class
was attached.}

  \item{11 Nov 2009: The 'type' argument does not make sense for plot.survfit.  (If 
type='p', should one plot the tops of the step function, the bottoms, or
both?).  Make it explicitly disallowed in response to an R-help query,
rather than the confusing error message that currently arose.}

  \item{28 Oct 2009: The basehaz function would reorder the labels of the strata
factor.  Not a bug really, but a "why do this?"  Unintended consequence of
a character -> factor conversion.}

  \item{1 Oct 2009: Fix a bug pointed out by Ben Domingue.  There was one if-then-else
path into step-halving in the frailty.controldf routine that would refer to
a non-existent variable.  A very rarely followed path, obviously, and with
the obvious fix. The mathematics of the update was fine.}

  \item{30 Sep 2009: For coxph and model.matrix.coxph, re-attach the
attributues lost from the X matrix when the intercept is removed,
i.e., X <- X[,1].  In particular, some downstream libraries depend on
the assign attribute. 
  For predict.coxph remove an earlier edit so that a single variable model
+ type='terms' returns a matrix, not a vector.  This is expected by the 
termplot() function.  It led to a whole lot of changes in the test suite
results, though, due to more "matrix" printouts.}

  \item{4 Sep 2009: Added a model.matrix.coxph and model.frame.coxph methods.  The
model.matrix.default function ceased to work for coxph models sometime
between R 2.9 and 2.9.2 (best guess).  This wasn't picked up in the test
suite but rather by failure of 3 packages that depend on survival.  Also added
a test.  Update CRAN since this broke other's packages.}

  \item{20 Aug 2009: One more fix to predict.coxph.  It needed to use 
delete.response(Terms) rather than Terms, so as to not look for (unnecessarily)
the response variable when the newdata argment is used.  Pointed out by Michael
Conklin.}

  \item{17 Aug 2009: Small bug in survfit.coxph.null pointed out by Frank Harrell.  The
'n' component would be missing if the input data included strata, i.e., the
initial model had used x=TRUE.  He also pointed out the fix.}

  \item{10 June 2009: Fix an error pointed out by Nick Reich, who was the first to use
interval censored data + user defined distribution in survreg, jointly.  There
was no test case and creating one uncovered several errors (but only for this
combination).  All the error cases led to catastrophic failure, highlighting
the extreme rarity of a user requesting this combination.}

  \item{2 June 2009: Surv(time1, time2, status, type='interval') would fail for an NA
status code.  Pointed out by Achim Zeilus.}

  \item{22 May 2009: Allow single subscripts to rate tables, e.g. survexp[1:10: .  
Returns a simple vector of values.  The str() function does this to print out
a short summary.  Problem pointed out by Heinz Tuechler.}

  \item{21 May 2009: Create a test case for factor variables/newdata/predict for coxph 
and survreg.  This led to a set of minor fixes; the code is now in line with
the R standard for model functions.  One consequence is that model.frame.coxph
and model.frame.survreg are no longer needed, so have been removed.}

  \item{20 May 2009: The manual page for survfit was confusing, since it tries to 
document both the standard KM (formula method) and the coxph method.  I've
split them out so that now survfit documents only the basic method and points 
a user the appropriate specialized page.}

  \item{1 May 2009: The anova.coxph function was incorrect for models with a strata
term.  Fixed this, and made chisquare tests the default.}

  \item{22 April 2009: The coxph code had an override to iter and eps, making both of
them more strict for a penalized model.  However, the overall default values
have changed over time, so that these lines actually decreased accuracy - the
opposite of their intent.  Removed the lines.  Also removed the iter.miss and
eps.miss components (on which this check depended) from coxph.control, which
makes that function match its documentation.}

 }
}

\section{Changes in version 2.34 and earlier}{
\subsection{Merge of the TMT source code tree with the Lumley code tree}{
 \itemize{

  \item Issues/decisions in remerging the Mayo and R code: 
  For most of routines, it was easier to start with the Lumley code and add
the Therneau fixes.  This is because Tom had expanded a lot of partial 
matches, e.g., fit$coef in the TT code vs fit$coefficients.  Routines with
substantial changes were, of course, a special case.
  The most common change is an is.R() construct to choose class vs oldClass.
  \item xtras.R: Move anova.coxph and anova.coxphlist to their own
  source files.
  The remainder of the code is R only.

  \item survsum: removed from package

  \item survreg.old: has been removed from the package

  \item survfit.s: 
   Depreciate the "formula with no ~1" option
   Mayo code for [ allows for reordering curves
   Separate out the R "basehaz" function as a separate source file

  \item survfit.km.s: The major change of did not get copied into R, so lots of
changes.  R had "new.time" and Splus 'start.time' for the same argument.  Allow
them both as synonyms.
   The output structure also changed: adapt the new one.  This is mostly some
name changes in the components, removing unneeded redundancies created by
a different programmer. 

  \item survfit.coxph.s:  TMT code finally fixed the "Can't (yet) to case weights" 
problem.  There must have been 10 years been the intent and execution. 

  \item survexp.s:  Add "bareterms" function from R, which replaces a prior use of
  terms.inner (in Splus but not R). 

  \item survdiff.s: R code had the old (incorrect) expected <- sum(1-offset), since
corrected to sum(-log(offset)) . 

  \item{summary.coxph.s: This was a mess, since Tom and I had independently made the
 addition of a print.summary.coxph function.  Below, TMT means that it was the
 choice in the Splus code, TL means that it was the choice in R
	1. Put the coef=T argument in the print function, not summary (TMT)
	2. Change the output's name from coef to coefficients (suggestion of
  Peter Dalgaard).  Also change one column name to Pr(>|z|) for R.
	3. Remove last vestiges of a reference to the 'icc' component (TMT)
	4. Do not include score, rscore, naive.var in the result (TL)
	5. Do include loglik in the result (TMT)
	6. Compute the test statistics (loglik, Wald, etc) in the summary
   function rather than in the print.summary function (TL)
	7. Remove the digits option from summary, it belongs in print.summary.
   (neither)}

  \item{strata.s: R code added a sep argument, this is ok
     R changed the character string NA to as.character(NA).  Not okay
          1. won't work with Splus, 
          2. This is a label, designed for printing, 
	          and so it should be a character string.  }

  \item{residuals.coxph.s: R had added type='partial'.  (Which I'm not very partial to,
  from their statistical properties.  But they are legal, and I assume that
  someone requested them).}

  \item{print.survfit.s: Rewritten as a part of the general survival rewrite.  Created
the function 'survmean' which does most of the work, and is shared by print and
summary, so that the values from 'print' are now available.
   Fix the minmin function: min(NULL) gives NA in Splus, which is the right
answer for a non-estimable median, but Inf in R.  Explicitly deal with this
case, and add a bunch of comments.
   R had the print.rmean option, this has been expanded to a more general
rmean option that allows setting the cutoff point.
   R added a print.n option with 3 choices, my code includes all 3 in the 
output.  }

  \item{lines.survfit.s: 
    The S version has a new block of code for guessing "firstx" more
intellegently when it is missing.  (Or, one hopes is is more intellegent!)}

  \item{coxph.control.s: 
   The R code had tighter tolerances (eps= 1e-9) than Splus (1e-4) and
a higher iterationn count (20 vs 10). 
   Set eps to 1e-8 and iter to 15, mostly bending to the world.  The tighter
iteration is defensible, but I still maintain that a Cox model that takes >10 
iterations is not going to finish if you give it 100.  The likelihood surface
is almost perfectly quadratic near the minimum.  (Not true for survreg by the
way).}

  \item{: In Surv, the Mayo code creates NA's out of invalid status values or
start,stop pairs, rather than a stop and error message.  This is to
allow for example
       coxph(Surv(time1,time2, status).... , subset=(goodlines))
succeed, when "goodlines" is the subset with correct values.}
}
}

\subsection{Older changes}{
 \itemize{
   \item{25SepO7: How embarrassing -- someone pointed out that I had Dave
     Harrington's name spelled wrong in the options to survfit.coxph!}

  \item{9Jul07: In a model with offsets, survreg mistakenly omitted the offset
from the returned linear.predictor component.}

  \item{10May07: Change summary.coxph so that it returns an object of class
summary.coxph, and add a print method for that object.}

  \item{22Jun06: Update match.ratetable, so that more liberal matches are now
allowed.  For instance,  'F', 'f', 'female', 'fem', 'FEMA', etc are 
now all considered matches to the dimname "female" in survexp.us.}

  \item{26Apr06: Fix bug in summary.survfit, pointed out by Bob Treder.  With
the times option, the value of n.risk would be wrong for "in between"
times; e.g., the data had events and/or censoring at times 10,
20,... and we asked for printout at time 15.  It should give n.risk at time
20, it was returning the value at time 10. Interestingly, the code had
a very careful treatment of this case, along with an example in the
comments, and the "the right answer is" part of the comment was wrong!
So the code correctly computed an incorrect answer.  Added another
test case to the test suite, survtest2.}

  \item{21Apr06: Fix problem in [.survfit, pointed out by Thomas Lumley.  If
fit <- survfit(Surv(time, status) ~ ph.ecog, lung), then fit[2:1] did
not reorder the output correctly.  I had never tested putting the 
subscripts in non-increasing order.}

  \item{7Feb06: Fix a problem in the coxph iteration (coxfit2.c, coxfit5, agfit3,
agfit5, agexact).  It will likely never catch anyone again, even if I 
didn't fix it.  In a particular data set, beta overshot and step halving
was invoked.  During step halving, a loglik happened to occur that was
within eps of the prior step's loglik --- and the routine decided, erroneously,
that it had converged!  (A nice quadratic curve, a first guess b1 to the 
left of  the desired max of the curve.  The next guess b2 overshot and ends 
up with a lower loglik, on the right side of the max.  Back up to the 
midpoint of b1 and b2, and this guess, still to the right of the max (still
too large) has EXACTLY the same value of y as b1 did, but on the other side
of the max from b1.  "Last two guesses give the same answer, I'm done" said
the routine).}

  \item{27Sep05: Found and fixed a nasty bug in survfit.  When method='fh2' and
there were multiple groups I had a subscripting bug, leading to vectors
that were supposed to be the same length, but weren't, passed into C.
The resulting curves were obviously wrong -- survival precipitously drops 
to zero.}

  \item{5May05: Add the drop=F arg to one subscripting selection in survfit.coxph.
	        temp <- (matrix(surv$y, ncol=3))[ntime,,drop=F] 
If you selected only 1 time point (1 row) in the final output, the code
would fail.  Pointed out by Cindy Crowson.}

  \item{18Apr05: Bug in survfit.turnbull.  The strata variable was not being
filled in (number of points per curve).  So if multiple curves were
generated at once, i.e., with something on the right hand side of ~ in
the formula, all the downstream print/plot functions would not work
with the result.}

  \item{8Feb05: Fix small typo in is.ratetable, introduced on 24Nov04: (Today
was the first time I added to the standard library, and thus ended
up using the non-verbose mode.)}

  \item{8Feb05: Add the data.frame argument to pyears.  This causes the output
to contain a dataframe rather than a set of arrays.  It is useful for
further processing of the data using Poisson regression.}

  \item{7Feb05: Modified print.ratetable to be more useful.  It now tells 
about the ratetable, rather than printing all of its values.}

  \item{8Dec04: Fix a small bug in survfit.turnbull. If there are people left 
censored before the first
time point of any other kind (interval, exact, or right censored),
the the plotted height of the curve from "rightmost left censoring time"
to "leftmost event time", that is the flat tail on the left, was at
the wrong height.
  Added another test to testreg/reliability.s for this.}

  \item{24Nov04: Change is.ratetable to give longer messages}
}
}
}