*C files: Change encoding to utf-8 so my name in comments is readcorrectly.
ltx2: Fix bugs in output.
GB_zeroin: C files removed.
AddlogLik methods tocoxreg andphreg.
coxreg:drop1 method added, handles missingvalues.
ltx2: New generic function. Similar to ltx, but printsconfidence limits instead of standard errors. Prints LRT p-values,automatic use of drop1.
hazards.coxreg: Add start at zero to cumulative hazardsplotting.
make.communal: Deal with zero length interval output andallow input for ‘com.dat’ with more than one variable.
Vignettes updated.
swepop, swedeaths: Data for the year 2020included.
plot.tpchreg: Error with arguments ‘xlab’ and ‘ylab’fixed.
coxreg: In case of request for bootstrap, ‘boot.sd’ isno longer calculated and returned: Caused too frequent errors due to illbalanced bootstrap samples, and was not really helpful anyway.
regtable: New function for creating simple regressionoutput tables.
pchreg: New function, to replace phreg(…, dist =“pch”).
phreg: ‘dist = “pch”’ deprecated.
age.window: No warning for an empty result, returns NULLin that case.
compHaz: New function, graphically comparing cumulativehazards.
plotHaz: New argument ‘interval’.
hazards: Add method for aftreg objects.
hazards: Bug with ‘pfixed = TRUE’ fixed.
print.summary.aftreg: Error in heading fixed.
tpchreg: try for singular hessian, continue withouterror.
ltx: Move caption to top of table (not really a bugfix).
ltx.tpchreg: Bug fix (really!)
ltx.phreg: Remove double printing of last fewrows.
init.c: Fix internal bug in ‘breslow_rs2’.
ltx: Introduce for tables.
hazards: New generic function calculating baselinehazards from fits. Methods for regression outputs.
logrank: New function performing a log-rank test. A plotmethod comes with it.
coxfunk: New function for calculating partial likelihoodwith derivatives.Warning: Under development, do nottrust results yet!
summary method totpchreg with aprintmethod.
Two new data sets,swepop andswedeaths:Tabular statistics, Sweden 1968-2019.
The data setswepop07 removed, replaced by swepop andswedeaths.
coxreg: Add log likelihood and df to nullmodels.
The data setchild is expanded with info aboutmother.
print.summary.coxreg: New argument ‘short’added.
plot.phreg: Argument ‘new.data’ removed, ‘score’added.
Gompertz: Argument ‘rate’ added to allfunctions.
risksets: New argument ‘collate_sets’, a logical.Defaults to FALSE, which conserves old behaviour. If TRUE, output is alist of lists, where each level 2 list describes one risk set.
coxreg: New argument ‘coxph’ (logical) is introduced. IfTRUE, survival::agreg.fit (or survival::coxph.fit) is called for in theoptimization. If FALSE, ‘own’ optimization is called for, can be slowfor (even moderately) large data sets (many distinct event time points).Default value is TRUE.
coxreg: Arguments ‘hazards’ and ‘center’deprecated.
phreg: Argument ‘center’ deprecated.
coxreg, phreg, aftreg: Fixed bug in calculating weightedmeans, which affects dates as covariates.
plot.hazdata: Fix y limits.
coxreg: Add stratum names when no covariates.
survival moved from Depends to Imports.
summary: Failed for null models with tpchreg, pchreg,now fixed.
summary.phreg: Bug fixed. It was introduced bydifferences between the distribution ‘pch’ and the other distributions.The piecewise constant hazards regression will eventually break out ofphreg and form a separate function, named ‘pchreg’. Have the samethoughts about the Gompertz distribution, to be put in ‘gompreg’. We’llsee… Main reason is that these guys need special treatment in theprogramming.
phreg: Fix issue with ‘shape =’ somethingpositive.
gompstartRate: Simpler starting values introduced(internal).
getsums.f: Replace ‘dcopy’ in three instances to pleasegfortran 10.
risksets: Bug fix: Now works when members =FALSE.
Rewritingtpchreg.
Add tpchreg methods: print, plot, extractAIC.
Add new function:oe (for occurrence/exposuredata).
Submit to CRAN.
tpchreg: Preparations for pretty-printing.
print.tpchreg: Printing method for tpchreg objectsintroduced.
More fixes to work around the gfortran bug.
Add C wrapper, cdgemv, for Fortran call to BLAS subroutinedgemv.
risksets: Warning about sample_fraction fixed.
Errors inplot.aftreg fixed (thanks to MarkClements).
Ineha_fun.c, changed ‘finite’ to ‘isfinite’(C99).
Fixtpchreg withextractAIC andnobs.
New functionstpchreg andtoTpch.
Bug inphreg, Gompertz distribution, ‘param =“rate”’,fixed.
Bug inphreg, Gompertz distribution, ‘param =“rate”’,with strata, fixed.
Error inplot.phreg, Gompertz with ‘param = “rate”’fixed.
New function:mpch gives the mean of a piecewiseconstant hazards distribution.
The functionplot.Surv is removed, since it now is aplot method from the survival package, which eha depends on. Note thoughthat this implies a new set of arguments. See the help page ofsurvival:::plot.survfit.
New versioning system (Hadley Wickham’ssuggestion).
Documentation ‘roxygenized’.
Development moved togitHub.
The packageglmmML was merged intoeha in version 2.0. This has turned out to be avery bad idea (“double entry”), and all relevant functions arenowDefunct and removed. UseglmmMLinstead.
glmmML(),glmmboot(),ghq(),glmmbootFit(),glmmML.fit() are allDefunct andremoved.Noreverse dependency used any of them. Those functions are allfound in the packageglmmML, on CRAN.
phreg(): Start values by ‘coxreg’ (bad idea)removed.
aftreg(): in ‘addMeans’ and ‘aftreg1’, an error(spotted by Jingchunzi Shi) with fixed scale corrected.
init.c: Added after R-3.4.0.
coxreg(): “Geometric bootstrap” removed (it neverworked and was never used).
cal.window(),age.window(): Works nowwith ‘tibbles’.
rpch: Bug fixed (spotted by Brigitte Mueller).
plot.phreg: parameters ‘changeLog’ and ‘…’ enhanced.Documentation updated.
plot.coxreg: Bug concerning ‘printLegend’ fixed.
weibreg: Note added in documentation: “Use phreg instead”.weibreg will soon be deprecated.
coxreg: Changed the default for ‘hazards’ to TRUE.
getHaz: Modified to handle missing strats and score.
print.risksets: Added ‘…’ to argument list.
coxreg: Fitting a NULL model didn’t produce enough informationlike log likelihood (‘loglik’), for comparison of models.Fixed.
glmmboot: ‘frail’ set to Inf or -Inf for appropriateclusters.
plot.hazdata: Updated to acknowledge the argument ‘hazards’ thatwas included in ‘coxreg’ in version 2.4-2.
plot.coxreg: Updated to acknowledge the argument ‘hazards’ thatwas included in ‘coxreg’ in version 2.4-2. Errors in the manual pagecorrected.
risksets: Risk set sampling did not always work (memory leak in Ccode); fixed.
risksets: New value in the Value list: sample_fraction.
plot.aftreg: Now registered as an S3 method.
print.aftreg: Scale and shape parameters are only printed on thelog scale.
src: ‘abs’ corrected to ‘fabs’ in two places in C code.
coxreg: Argument ‘hazards’ added, with default = FALSE.
plot.Surv: Argument ‘printLegend’ added.
coxreg: Changed labels in case of ordered factors.
Foreign calls: ‘DUP = FALSE’ removed everywhere.
print.pch: Bug preventing printing(!) fixed.
plot.pch: Bug preventing plotting(!) fixed.
coxreg: Call to survival::[agreg,coxph].fit in “standard” casesreintroduced; Thanks to Terry Therneau, who exports these functions fromsurvival_2.37-6. So this version of ‘eha’ requires survival (>=2.37-6). Argument ‘center’ reintroduced, with slightly differentmeaning.
plot.coxreg: argument ‘newdata’ not used.
phreg: Stratified analysis in the piecewise constant hazardsmodel introduced. Argument ‘center’ reintroduced, with slightlydifferent meaning.
plot.phreg: Argument ‘newdata’ not used.
plot.coxreg: added the argument col, for color line(s).
plot.hazdata: Ditto.
coxreg: Restoring equity.
glmmML: Removed spurious printing in ‘glmmml.c’.
coxreg: ‘Downgraded’ due to limitations in using non-exportedfunction (agreg) from ‘survival’. This will be taken care of ASAP.Meanwhile, live with slightly slower ‘coxreg’ and choking on huge datasets.
Coxreg: Removed for the same reason as the downgrade ofcoxreg.
phreg: The lognormal and loglogistic distributions have anintercept added to the linear predictor; in effect extending thesedistributions to three-parameter families. A bug (found by ClaireWilliams) affecting the covariance matrix of the parameter estimates hasbeen eliminated.
aftreg: The same bug as for phreg eliminated. The availableparametrizations are changed to ‘lifeAcc’ and ‘lifeExp’. For theGompertz distribution, the ‘canonical’ representation is usedregardless.
hlnorm, Hlnorm, hllogis, Hllogis: New parameter, ‘prop’, added.It simply multiplies the previous definitions by its value.
age.window, cal.window: speed up and handling of emptyintervals
perstat: speed up.
plot.phreg, plot.coxreg: legend added for stratifiedfits.
Coxreg: New function designed to handle huge data sets. coxregchokes on ‘integer overflow’, and memory overflow, when the collectionof risk sets is created and saved. Coxreg is essentially a wrapper for‘coxph’ in the ‘survival’ package, but with methods for nice(r)printing.
coxreg: Error in the calculation of ‘total time at risk’ fixed(gave negative values when no left truncation!).
phreg: The gompertz ‘scale’ parameter is now a real scaleparameter through a reparametrization of the baseline gomperzdistribution. It follows now the ‘canonical’ parametrization. There isalso a new argument, ‘param’, which can take the values “canonical”(default) and “rate”. Better start values for the Gompertzregressions.
check.dist : Has failed due to different scaling in coxreg andphreg since 2.2-2. Now fixed.
risksets: Added an argument, ‘members’, a logical with defaultvalue ‘TRUE’. If TRUE, the members of all risk sets are returned. Withhuge data sets, this may be too much, and not wanted. In such cases, set‘members = FALSE’.
coxreg: Memory leaks fixed in getHaz.f, sizes.c andrisk.c.
Gompertz distribution: new parameter ‘param’; values ‘default’(default, nothing changes), and ‘canonical’, which gives meaning ‘PH’and ‘AFT’ to the shape and scale parameters, respectively.
aftreg: New input argument: ‘param’, with three values, ‘default’(which is the default;), ‘survreg’, and ‘canonical’. The value ‘default’uses the standard parametrization, while ‘survreg’ uses the sameparametrization as the survreg function in the survival package.‘canonical’ is especially useful in the Gompertz distribution forseparating PH and AFT parameters.
C code cleaned (avoiding some Warnings at CRAN).
check.dist: New argument, col, added. Default is nowblack-and-white plotting.
ltx: New function for printing coxreg fits in latexformat.
plot.Surv: New arguments, col and lty, added. The default is nowblack-and-white plotting.
data: Two new data sets, “logrye” and “scania”.
oldmort: Data set updated.
aftreg.fit: Errors in documentation corrected.
SurvSplit: Bug fixed. It works now.
glmmboot: Bug in calculation of ‘frail’ fixed.
plot.phreg: Bug in argument ‘ylim’ fixed. Bug with stratifiedfits fixed.
aftreg, phreg: summary method added (just printing).
glmmML: Merged into eha. This adds binary and count dataregression for clustered data to eha. glmmML is still a standalonepackage on CRAN, for how long remains to be seen.
Pch: New class of distributions; Piecewise constant hazards(Pch).
phreg: piecewise constant baseline hazard functionintroduced.
phreg: ‘center’ reinstalled as a logical, default = TRUE, sonothing changes if ‘center’ is left untouched.
age.window: If the selected window is empty, an error waspreviously thrown. Now NULL is returned, with a warning.
cal.window: Now returns NULL, with a warning, if the selectedwindow is empty.
aftreg: Gompertz distribution added (back again). Better startvalues.
phreg: Better start values for Gompertz distribution.
eha: Depends (R >= 2.13.0)
phreg, aftreg, weibreg: Errors in documentationcorrected.
ChangeLog: Errors in 1.3-6 corrected.
coxph, phreg, aftreg: Bug fix: Logical covariates now OK.(converted to factor).
phreg: Removed “coxph” from “class”.
aftreg: Ditto.
weibreg: Ditto.
oldmort: New data set.
coxreg: added return values ‘df’ and ‘n’.
coxreg, phreg, aftreg: Added extractAIC and nobsmethods.
toBinary: Now includes also risksets without survivors (ifany).
fert: Row names changed to row numbers.
swe07: New data set.
Spelling errors (some!) corrected in documentation.
male.mortality: Old name (male.mortality) of data frame mortreinstalled. Now known under two names. Overlapping spells no longerexist.
fert: Documentation corrected.
toDate: Now works as intended.
* dllogis: Bug fixed.* hllogis: Bux fixed.phreg: Fixed error and (some) numerical instability in theestimation of the Gompertz proportional hazards model (seems to be verydependent on good start values!).
plot.phreg: Fixed ‘ylim’ for cumulative hazards plot.
male.mortality: Data set renamed to
mort: The new name. (Just for convenience!)
coxreg: Major revision, calls ‘coxph’ in ‘survival’ (thanks toTerry Therneau!) for ordinary requests. Reason: speed. The argument‘center’ is deprecated, centering of covariates is now routinely made.Affects the estimation of the baseline hazard, which is done at themeans of the columns of the original design matrix.
phreg: Argument ‘center’ is deprecated. Centering is routinelyperformed, so the baseline hazard is estimated at the means of thecolumns of the original design matrix.
aftreg: Corrected error in documentation and made the argument‘center’ deprecated.
aftreg: Estimation of intercept (“scale”) is now comparable withcorresponding estimate of Intercept in ‘survreg’. ‘shape’ in aftreg isstill ‘1 / scale’ in survreg. Regression coefficients still havedifferent signs but the same absolute values.
join.spells: a few bugs fixed, now allows for factorcovariates.
male.mortality: data set “joined”.
fert: is a new data set. Contains data on 19th century maritalfertility from a parish in northern Sweden.
aftreg.fit: Check of data consistency in case of more than onerecord per individual added.
aftreg.fit: Fixed memory allocation bug in C code. This bug wasnot fatal (too much memory was allocated), but caused a severeperformance problem, especially on Windows.
aftreg: ‘dist = “gompertz”’ should now work (realizing that it isa special case of ’dist = “EV”).
phreg: Fixed bugs for the cases with fixed shape (includes ‘dist= “gompertz”’.
aftreg: ‘offset’ works now.
phreg: Ditto.
check.dist: Bug fixed for ‘dist = “gompertz”’ (again!)
plot.phreg: Ditto.
#eha 1.2-15
aftreg: argument ‘id’ now works as intended, i.e., is looked forin ‘data’ (or ‘parent.frame()’)
print: functions return invisibly ‘x’.
coxreg: argument ‘weights’ now works as intended, i.e., is lookedfor in ‘data’ (or ‘parent.frame()’)
check.dist: Bad ‘ylim’ fixed.
aftreg: Gompertz distribution had a bug; now fixed.
coxreg: Added (time-varying) weighted Cox regression. Returnserror code 1 if failure, with a warning.
check.dist: Can now handle stratified models.
Bugs in qEV, rEV, all Gompertz functions, plus documentation ofEV and Gompertz fixed. Note that these bugs did not affect aftreg orphreg! However,
check.dist had to be revised due to the above bugs.
Bug in coxreg, method = “ml” fixed.
Bug in coxreg, calculation of hazard, fixed.
Several errors in the documentation fixed.
* Added 'risktime' to toBinary output.Added full profiling to the “ml” and “mppl” methods incoxreg.
mlreg is now deprecated. Use coxreg with method = ml or =mppl
table.events: New parameter: ‘strict = TRUE’.
make.communal: In case of ‘communal=FALSE’, spells are no longertruncated. Instead a value of NA is given if birthdate is out of range.Previous behavior was unpredictable when birthdate was out ofrange.
mlreg: Geometric distribution (i.e., constant baseline discretehazard) added. Not for frailty models, yet (on the TODO list).
mlreg: New argument, ‘n.points’, added to ‘control’. Controls thenumber of points used in the Gauss-Hermite quadrature.
mlreg: Stricter control of numerical problems, especially in thefrailty fit.
clean: Replaced by check.spells and join.spells.
Return values changed to conform with R-1.8.0 (andlater).