Commit c5a187ee authored by Christopher Lawrence's avatar Christopher Lawrence Committed by Andreas Tille

Import Debian changes 1.03.6.1-1

r-cran-pscl (1.03.6.1-1) unstable; urgency=low

  * New upstream release.

r-cran-pscl (1.03.6-1) unstable; urgency=low

  * New upstream release.
parents a6b348d5 cf0ab2d0
Package: pscl
Version: 1.03.5
Date: 2010-04-12
Version: 1.03.6.1
Date: 2010-08-25
Title: Political Science Computational Laboratory, Stanford University
Author: Simon Jackman, with contributions from Alex Tahk, Achim
Zeileis, Christina Maimone and Jim Fearon
Maintainer: Simon Jackman <jackman@stanford.edu>
Depends: R (>= 2.3.0), MASS, stats, mvtnorm, coda
Depends: R (>= 2.11.0), MASS, stats, mvtnorm, coda, gam
Suggests: MCMCpack, car, lmtest, sandwich, zoo
Enhances: stats, MASS
Description: Bayesian analysis of item-response theory (IRT) models,
......@@ -18,6 +18,6 @@ LazyLoad: true
LazyData: true
License: GPL-2
URL: http://pscl.stanford.edu/
Packaged: 2010-04-13 01:51:28 UTC; jackman
Repository: CRAN
Date/Publication: 2010-04-13 07:15:01
Date/Publication: 2011-03-21 14:58:50
Packaged: 2011-03-21 12:57:49 UTC; ripley
1.03.6 * made gam dependency explicit
* change linear.hypothesis to linearHypothesis
1.03.5 * added AustralianElectionPolling
* tidy up Rd files for data sets (itemize -> describe)
* use dQuote in Rd files (or not)
......
......@@ -196,7 +196,7 @@ hurdle <- function(formula, data, subset, na.action, weights, offset,
mf <- eval(mf, parent.frame())
## extract terms, model matrices, response
mt <- terms(formula, data = data)
mt <- attr(mf, "terms")
mtX <- terms(ffc, data = data)
X <- model.matrix(mtX, mf)
mtZ <- terms(ffz, data = data)
......@@ -692,7 +692,7 @@ hurdletest <- function(object, ...) {
stopifnot(require("car"))
nam <- names(object$coefficients$count)
lh <- paste("count_", nam, " = ", "zero_", nam, sep = "")
rval <- car::linear.hypothesis(object, lh, ...)
rval <- car::linearHypothesis(object, lh, ...)
attr(rval, "heading")[1] <- "Wald test for hurdle models\n\nRestrictions:"
return(rval)
}
......
......@@ -160,7 +160,7 @@ zeroinfl <- function(formula, data, subset, na.action, weights, offset,
mf <- eval(mf, parent.frame())
## extract terms, model matrices, response
mt <- terms(formula, data = data)
mt <- attr(mf, "terms")
mtX <- terms(ffc, data = data)
X <- model.matrix(mtX, mf)
mtZ <- terms(ffz, data = data)
......
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
No preview for this file type
r-cran-pscl (1.03.5-1+deb70u1) testing-proposed-updates; urgency=low
r-cran-pscl (1.03.6.1-1) unstable; urgency=low
* Non-maintainer upload.
* replace-obsolete-pythag.patch: new patch, fixes FTBFS (Closes: #684823)
* New upstream release.
-- Chris Lawrence <lawrencc@debian.org> Tue, 22 Mar 2011 15:48:45 -0500
r-cran-pscl (1.03.6-1) unstable; urgency=low
* New upstream release.
-- Sébastien Villemot <sebastien@debian.org> Thu, 27 Sep 2012 21:15:23 +0200
-- Chris Lawrence <lawrencc@debian.org> Sat, 15 Jan 2011 11:02:38 -0600
r-cran-pscl (1.03.5-1) unstable; urgency=low
......
......@@ -2,13 +2,13 @@ Source: r-cran-pscl
Section: gnu-r
Priority: optional
Maintainer: Chris Lawrence <lawrencc@debian.org>
Build-Depends: debhelper (>> 7), cdbs, r-base-dev (>> 2.3.0), r-cran-mass, r-cran-mvtnorm (>= 0.7.5-2), r-cran-coda, r-cran-lattice
Standards-Version: 3.8.4
Build-Depends: debhelper (>> 7), cdbs, r-base-dev (>> 2.3.0), r-cran-mass, r-cran-mvtnorm (>= 0.7.5-2), r-cran-coda, r-cran-lattice, r-cran-gam
Standards-Version: 3.9.1
Homepage: http://pscl.stanford.edu/
Package: r-cran-pscl
Architecture: any
Depends: r-base-core (>> 2.3.0), r-cran-mass, r-cran-mvtnorm (>= 0.7.5-2), r-cran-coda, r-cran-lattice, ${shlibs:Depends}, ${misc:Depends}
Depends: r-base-core (>> 2.3.0), r-cran-mass, r-cran-mvtnorm (>= 0.7.5-2), r-cran-coda, r-cran-lattice, r-cran-gam, ${shlibs:Depends}, ${misc:Depends}
Suggests: r-cran-mcmcpack, r-cran-zoo, r-cran-sandwich, r-cran-lmtest, r-cran-car
Enhances: r-cran-mass
Description: GNU R package for discrete data models
......
Description: Use hypot instead of pythag
The pythag function has been definitely abandoned in favor of hypot in
R 2.14.0, see /usr/share/doc/r-base-core/changelog.gz
Origin: upstream, version 1.03.10
Bug-Debian: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=684823
Last-Update: 2012-08-27
---
This patch header follows DEP-3: http://dep.debian.net/deps/dep3/
--- a/src/pi.c
+++ b/src/pi.c
@@ -13,7 +13,7 @@
GetRNGstate();
for(i=0;i<*n;i++){
- d = pythag(unif_rand(),unif_rand());
+ d = hypot(unif_rand(),unif_rand());
if(d<1.0)
(*z)++;
}
replace-obsolete-pythag.patch
(TeX-add-style-hook "countreg"
(lambda ()
(LaTeX-add-bibliographies)
(LaTeX-add-labels
"sec:intro"
"sec:software"
"tab:overview"
"eq:family"
"eq:mean"
"eq:Poisson"
"eq:negbin"
"eq:hurdle"
"eq:hurdle-mean"
"eq:zeroinfl"
"eq:zeroinfl-mean"
"sec:illustrations"
"fig:ofp"
"fig:bad-good"
"fig:ofp2"
"tab:summary"
"sec:summary"
"app:hurdle"
"app:zeroinfl"
"app:methods"
"tab:methods"
"app:replication")
(TeX-add-symbols
'("fct" 1)
'("class" 1))
(TeX-run-style-hooks
"thumbpdf"
"latex2e"
"jss10"
"jss"
"nojss")))
......@@ -7,7 +7,7 @@
\newcommand{\class}[1]{``\code{#1}''}
\newcommand{\fct}[1]{\code{#1()}}
\author{Achim Zeileis\\Wirtschaftsuniversit\"at Wien \And
\author{Achim Zeileis\\Universit\"at Innsbruck \And
Christian Kleiber\\Universit\"at Basel \And
Simon Jackman\\Stanford University}
\Plainauthor{Achim Zeileis, Christian Kleiber, Simon Jackman}
......@@ -38,10 +38,10 @@
\Address{
Achim Zeileis\\
Department of Statistics and Mathematics\\
Wirtschaftsuniversit\"at Wien\\
Augasse 2--6\\
A-1090 Wien, Austria\\
Department of Statistics\\
Universit\"at Innsbruck\\
Universit\"atsstr.~15\\
6020 Innsbruck, Austria\\
E-mail: \email{Achim.Zeileis@R-project.org}\\
URL: \url{http://statmath.wu-wien.ac.at/~zeileis/}
}
......@@ -277,7 +277,7 @@ functions are complemented by further generic inference functions in
contributed packages: e.g., \pkg{lmtest} \citep{countreg:Zeileis+Hothorn:2002}
provides a \fct{coeftest} function that also computes partial Wald tests
but allows for specification of alternative (robust) standard errors. Similarly,
\fct{waldtest} from \pkg{lmtest} and \fct{linear.hypothesis} from \pkg{car}
\fct{waldtest} from \pkg{lmtest} and \fct{linearHypothesis} from \pkg{car}
\citep{countreg:Fox:2002} assess nested models via Wald tests (using
different specifications for the nested models). Finally, \fct{lrtest}
from \pkg{lmtest} compares nested models via likelihood ratio (LR) tests
......@@ -462,10 +462,10 @@ respectively. For details see Appendix~\ref{app:hurdle}.
A set of standard extractor functions for fitted model objects is available for
objects of class \class{hurdle}, including the usual \fct{summary} method that
provides partial Wald tests for all coefficients. No \fct{anova} method is provided,
but the general \fct{coeftest}, \fct{waldtest} from \pkg{lmtest}, and \fct{linear.hypothesis}
but the general \fct{coeftest}, \fct{waldtest} from \pkg{lmtest}, and \fct{linearHypothesis}
from \pkg{car} can be used for Wald tests and \fct{lrtest} from \pkg{lmtest}
for LR tests of nested models. The function \fct{hurdletest} is a convenience
interface to \fct{linear.hypothesis} for testing for the presence of a hurdle
interface to \fct{linearHypothesis} for testing for the presence of a hurdle
(which is only applicable if the same regressors and the same count distribution
are used in both components).
......@@ -544,7 +544,7 @@ a set of standard extractor functions for fitted model objects is available for
objects of class \class{zeroinfl}, including the usual \fct{summary} method that
provides partial Wald tests for all coefficients. Again, no \fct{anova} method is provided,
but the general functions \fct{coeftest} and \fct{waldtest} from \pkg{lmtest},
as well as \fct{linear.hypothesis} from \pkg{car} can be used for Wald tests,
as well as \fct{linearHypothesis} from \pkg{car} can be used for Wald tests,
and \fct{lrtest} from \pkg{lmtest} for LR tests of nested models.
......@@ -1124,7 +1124,7 @@ argument, the estimates for a single component can be extracted. Concatenating
the parameters by default and providing a matching covariance matrix estimate
(that does not contain the covariances of further nuisance parameters) facilitates
the application of generic inference functions such as \fct{coeftest}, \fct{waldtest},
and \fct{linear.hypothesis}. All of these compute Wald tests for which coefficient
and \fct{linearHypothesis}. All of these compute Wald tests for which coefficient
estimates and associated covariances is essentially all information required and
can therefore be queried in an object-oriented way with the \fct{coef} and \fct{vcov}
methods.
......@@ -1170,7 +1170,7 @@ Function & Description \\ \hline
\fct{logLik} & extract fitted log-likelihood \\ \hline
\fct{coeftest} & partial Wald tests of coefficients \\
\fct{waldtest} & Wald tests of nested models \\
\fct{linear.hypothesis} & Wald tests of linear hypotheses \\
\fct{linearHypothesis} & Wald tests of linear hypotheses \\
\fct{lrtest} & likelihood ratio tests of nested models \\
\fct{AIC} & compute information criteria (AIC, BIC, \dots) \\ \hline
\end{tabular}
......
No preview for this file type
......@@ -15,7 +15,7 @@ hurdletest(object, \dots)
\arguments{
\item{object}{A fitted model object of class \code{"hurdle"}
as returned by \code{\link{hurdle}}, see details for more information.}
\item{\dots}{arguments passed to \code{\link[car]{linear.hypothesis}}.}
\item{\dots}{arguments passed to \code{\link[car]{linearHypothesis}}.}
}
\details{
......@@ -26,13 +26,13 @@ hurdletest(object, \dots)
model.
The function \code{hurdletest} is a simple convenience interface to
the function \code{\link[car]{linear.hypothesis}} from the \pkg{car}
the function \code{\link[car]{linearHypothesis}} from the \pkg{car}
packages that can be employed to carry out a Wald test for this
hypothesis.
}
\value{
An object of class \code{"anova"} as returned by \code{\link[car]{linear.hypothesis}}.
An object of class \code{"anova"} as returned by \code{\link[car]{linearHypothesis}}.
}
\references{
......@@ -45,7 +45,7 @@ Cambridge: Cambridge University Press.
\author{Achim Zeileis <Achim.Zeileis@R-project.org>}
\seealso{\code{\link{hurdle}}, \code{\link[car]{linear.hypothesis}}}
\seealso{\code{\link{hurdle}}, \code{\link[car]{linearHypothesis}}}
\examples{
data("bioChemists", package = "pscl")
......
......@@ -43,7 +43,8 @@ zeroinfl(formula, data, subset, na.action, weights, offset,
is a Poisson or negative binomial regression (with log link).
The geometric distribution is a special case of the negative binomial
with size parameter equal to 1.
For modeling the unobserved state (zero vs. count), a binary model is used:
For modeling the unobserved state (zero vs. count), a binary model is used
that captures the probability of zero inflation.
in the simplest case only with an intercept but potentially containing regressors.
For this zero-inflation model, a binomial model with different links can be
used, typically logit or probit.
......
......@@ -13,7 +13,7 @@ void simpi(int *n, int *z)
GetRNGstate();
for(i=0;i<*n;i++){
d = pythag(unif_rand(),unif_rand());
d = hypot(unif_rand(),unif_rand());
if(d<1.0)
(*z)++;
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment