surveysd 2.0.0
CRAN release: 2025-08-26
Fixed issue if parameter
period
was typehaven::labelled
incalc.stError()
.Refactored code to make use of new
data.table
variableenv
. Makes code more readable and stable.-
calc.stError()
has new parametergroup.diff
. Ifgroup.diff=TRUE
differences between values defined ingroup
will also be calculated. For instancelibrary(surveysd) set.seed(1234) eusilc <- demo.eusilc(n = 4,prettyNames = TRUE) dat_boot <- draw.bootstrap(eusilc, REP = 3, hid = "hid", weights = "pWeight", strata = "region", period = "year") dat_boot_calib <- recalib(dat_boot, conP.var = "gender", conH.var = "region") # estimate weightedRatio for povertyRisk per period err.est <- calc.stError(dat_boot_calib, var = "povertyRisk", fun = weightedRatio, group = "gender", group.diff = TRUE)
will produce difference in poverty rate between
male
andfemale
, in addition to other estimates. Updated vignette accordingly.
Fixed bug with parameter
adjust.var
andfun.adjust.var
in functioncalc.stError()
.Changed parameter
national
torelative.share
incalc.stError()
included adeprecate
-message ifnational = TRUE
is supplied.Fixed issue with parameter
looseH
in functionipf()
.Fixed bug that variables names created by internal functions where not properly cleaned up before returning
data.table
output.Improved
summary.ipf()
and includedprint.summary.ipf()
in order to make the output ofipf()
as well as convergence issues when usingipf()
more intuitive.New parameter
method
indraw.bootstrap()
andrescaled.bootstrap()
. Can bei either"Preston"
or"Rao-Wu"
, see?draw.bootstrap()
or the new vignette.draw.bootstrap()
can now be used to draw bootstrap replicates if bootstrap replicates where drawn for previous year with parameteralready.selected
.already.selected
expects a list ofdata.table
s indicating if a record was already included in a bootstrap replicates in the previousperiod
New function
get.selection()
to create input for parameteralready.selected
indraw.bootstrap()
.Updated and included (more) unit tests.
surveysd 1.3.2
-
rescaled.bootstrap()
has additional parameterperiod
which is identical to the one indraw.bootstrap
. Ifperiod
is notNULL
the boostraps will be drawn such that in each period and strata/cluster only $\floor{\frac{n}{2}}$ records are drawn. This produces more consisten results and should make calibration afterwards easier. - Improved numerical weighting with
computeLinearG1
for use withipf()
.computeLinearG1
is now more stable when only numerical variables are used for weighting. - parameter
numericalWeighting
can be passed torecalib
and will correctly be passed along to functionipf
surveysd 1.3
- new parameter minMaxTrim in
ipf()
to trim weights - fix bug for numericalWeighting reported “converged” when it did not converge
- fix bug when checking cluster and strata for bootstrapping
surveysd 1.1.1
-
recalib()
accepts conP and conH in the same way asipf
-
recalib()
has argumentsepsP
andepsH
, to make convergence limits more transparant - fixed bug in
ipf()
when supplyinghid="hid"
, see https://github.com/statistikat/surveysd/pull/20. Thanks @asiripanich
surveysd 1.1.0
CRAN release: 2019-07-15
- uncouple surveysd from simPop
- use
demo.eusilc()
for all examples and unit tests in this package - remove simPop from the “Suggests” field (DESCRIPTION)
- use
- remove hardcoded variable names in default parameters
- allow calls to
recalib()
without specifyingconP.vars
orconH.vars
surveysd 1.0.1
- fix bug with fpc calculation (0824834)
- fix bug with dummy data (5adb6b7)
- improve readability of code and resolve linters
- resolve issues when datasets have columns with certain names (#7, #10)
- automatize the gh-pages builds
- css updates
- automated linter-checking
- new badges (code coverage, cran)
- update setup for vignettes
- fix issue when household column is not a factor (#12)
surveysd 1.0.0
CRAN release: 2019-01-25
- copy
simPop::ipu2()
and some related functions to surveysd.- add bugfixes for ported functions
- simplify tests
- update references for the methodology vignette
- fix sampling with full population in some strata
surveysd 0.2.1
- Create vignette for error estimation
- Bugfixes for plotting and
...
argument incalc.stError
- Documentation updates. Make example plots available in gh-pages
surveysd 0.2.0
- Automatically pass variable names for household id, weights and reference period from
draw.bootstrap
to downstream functions - Reorganize names of R source files
Documentation updates
- Use markown pre-processing for documentation
- Add github pages, more badges and a logo
- export
draw.bootstrap
and includeprettyNames
argument. update documenentation examples to use new variable names - Don’t load
laeken
anddata.table
in examples - rewrite
vignettes/TheoryWord.Rmd
into a dynamic markdown file describing the methodology of the package