Path to this page:
Next  Query returned 5 messages, browsing 1 to 10  previous
CVS Commit History:
20230608 18:04:37 by Makoto Fujiwara  Files touched by this commit (2) 
Log message:
(math/Rsandwich) Updated 3.0.1 to 3.0.2
# sandwich 3.02
* Added new argument `aggregate = TRUE` to `meatPL()` which is thus inherited by
`vcovPL()`. By default, this still yields the Driscoll & Kraay (1998) \
covariance
matrix. When setting `aggregate = FALSE` the crosssectional and crossserial
correlation is set to zero, yielding the "pure" panel NeweyWest \
covariance
matrix.
* Bug fix in `vcovCL(..., type = "HC2")` for `glm` objects or `lm` objects
with weights. The code had erroneously assumed that the hat matrices were
all symmetric (as in the `lm` case without weights). This is corrected now.
(Detected and reported by Bixi Zhang.)
* Issue a warning in `vcovHC()` for HC2/HC3/HC4/HC4m/HC5 if any of the hat values
are numerically equal to 1. This leads to numerically unstable covariances,
in the most extreme case `NaN` because the associated residuals are equal to
0 and divided by 0. (Suggested by Ding Peng and John Fox.)
* Speed improvement in `vcovBS.lm()`: For `"xy"` bootstrap, \
`.lm.fit()` rather than
`lm.fit()` is used which is somewhat more efficient in some situations (suggested
by Grant McDermott). For `"residual"` and wild bootstrap, the \
bootstrap by default
still samples coefficients via QR decomposition in each iteration (`qrjoint = \
FALSE`)
but may alternatively sample the dependent variable and then apply the QR
decomposition jointly only once (`qrjoint = TRUE`). If the sample size (and the
number of coefficients) is large, then `qrjoint = TRUE` may be significantly faster
while requiring much more memory (proposed by Alexander Fischer).
* Enable passing score matrix (as computed by `estfun()`) directly to
`bwAndrews()` and `bwNeweyWest()`. If this is used, the score matrix should
either have a column `(Intercept)` or the `weights` argument should be set
appropriately to identify the column pertaining to the intercept (if any).
* The vignettes have been tweaked so that they still "run" without \
technical errors
when suggested packages (listed in the VignetteDepends) are not available. This is
achieved by defining replacement functions that do not fail but lead to partially
nonsensical output. A warning is added in the vignettes if any of the replacements
is used.

20211026 12:56:13 by Nia Alarie  Files touched by this commit (458) 
Log message:
math: Replace RMD160 checksums with BLAKE2s checksums
All checksums have been doublechecked against existing RMD160 and
SHA512 hashes

20211007 16:28:36 by Nia Alarie  Files touched by this commit (458) 
Log message:
math: Remove SHA1 hashes for distfiles

20210918 13:43:01 by Makoto Fujiwara  Files touched by this commit (2) 
Log message:
(math/Rsandwich) Updated 2.5.1 to 3.0.1
# sandwich 3.01
* Extended the "Getting started" page with information on how to use \
_sandwich_ in
combination with the _modelsummary_ package (ArelBundock) based on _broom_
infrastructure (Robinson, Hayes, Couch). (Based on ideas from Grant McDermott.)
<https://sandwich.RForge.Rproject.org/articles/sandwich.html>
* Catch `NA` observations in `cluster` and/or `order.by` indexes for `vcovCL()`,
`vcovBS()`, `vcovPL()`, and `vcovPC()`. Such missing observations cannot be
handled in the covariance extractor functions but need to be addressed prior
to fitting the model object, either by omitting these observations or by
imputing the missing values. (Raised by Alexander Fischer on StackOverflow
\
<https://stackoverflow.com/questions/64849935/clusteredstandarderrorsandmissingvalues>.)
* In `vcovHC()` if there are `estfun()` rows that are all zero and `type = \
"const"`,
then the working residuals for `lm` and `glm` objects are obtained via
`residuals()` rather than `estfun()`. (Prompted by an issue raised by
Alex Torgovitsky.)
# sandwich 3.00
* Release of version 3.00 accompanying the publication of the paper
"Various Versatile Variances: An ObjectOriented Implementation of
Clustered Covariances in R." together with Susanne Koell and Nathaniel Graham
in the _Journal of Statistcal Software_ at \
<https://doi.org/10.18637/jss.v095.i01>.
The paper is also provided as a vignette in the package as
`vignette("sandwichCL", package = "sandwich")`.
* Improved or clarified notation in Equations 6, 9, 21, and 22 (based on
feedback from Bettina Gruen).
* The documentation of the HC1 bias correction for clustered covariances
in `vignette("sandwichCL", package = "sandwich")` has \
been corrected (Equation 15).
While both the code in `vcovCL()` and the corresponding documentation `?vcovCL`
always correctly used (n1)/(nk), the vignette had incorrectly stated it as
n/(nk). (Reported by Yves Croissant.)
* The package is also accompanied by a `pkgdown` website on RForge now:
<https://sandwich.RForge.Rproject.org/>
This essentially uses the previous content of the package (documentation,
vignettes, NEWS) and just formatting was enhanced. But a few new features
were also added:
 A "Get started" vignette for the `pkgdown` page (but not shipped in the
package) providing an introduction to the package and listing all
variancecovariance functions provided with links to further details.
 R/Markdown overview vignettes for the `pkgdown` page (but also not shipped
in the package) linking the `Sweave`based PDF vignettes so that they are
easily accessible online.
 A `README` with very brief overview for the `pkgdown` title page.
 A nice logo, kindly provided by Reto Stauffer.
* All kernel weights functions in `kweights()` are made symmetric around zero now
(suggested by Christoph Hanck). The quadratic spectral kernal is approximated
by `exp(c * x^2)` rather than `1` for very small `x`.
* In case the `Formula` namespace is loaded, warnings are suppressed now for
processing formula specifications like `cluster = ~ id` in `expand.model.frame()`.
Otherwise warnings may occur with the `` separator in multipart formulas with
factors. (Reported by David HughJones.)
* The `bread()` method for `mlm` objects has been improved to also handle
_weighted_ `mlm` objects. (Suggested by James Pustejovsky.)

20190808 21:53:58 by Brook Milligan  Files touched by this commit (189)  
Log message:
Update all R packages to canonical form.
The canonical form [1] of an R package Makefile includes the
following:
 The first stanza includes R_PKGNAME, R_PKGVER, PKGREVISION (as
needed), and CATEGORIES.
 HOMEPAGE is not present but defined in math/R/Makefile.extension to
refer to the CRAN web page describing the package. Other relevant
web pages are often linked from there via the URL field.
This updates all current R packages to this form, which will make
regular updates _much_ easier, especially using pkgtools/R2pkg.
[1] http://mailindex.netbsd.org/techpkg/2019/08/02/msg021711.html

Next  Query returned 5 messages, browsing 1 to 10  previous