[Lme4-commits] r1832 - in pkg/lme4.0: . man tests
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Fri Aug 9 13:50:33 CEST 2013
Author: mmaechler
Date: 2013-08-09 13:50:33 +0200 (Fri, 09 Aug 2013)
New Revision: 1832
Modified:
pkg/lme4.0/DESCRIPTION
pkg/lme4.0/man/convert_old_lme4.Rd
pkg/lme4.0/tests/lmer-1.R
pkg/lme4.0/tests/lmer-1.Rout.save
Log:
convert_old help page; cosmetics
Modified: pkg/lme4.0/DESCRIPTION
===================================================================
--- pkg/lme4.0/DESCRIPTION 2013-08-09 11:18:57 UTC (rev 1831)
+++ pkg/lme4.0/DESCRIPTION 2013-08-09 11:50:33 UTC (rev 1832)
@@ -1,13 +1,15 @@
Package: lme4.0
Version: 0.999999-3
-Date: 2013-07-04
+Date: 2013-08-09
Title: Linear mixed-effects models using S4 classes
Description: Fit linear and generalized linear mixed-effects models.
- This is the implementation of lme4 available on CRAN and developed up to 2011.
- It has been renamed to lme4.0, and is now deprecated in favor of the new lme4 package.
- For the time being, code and other packages who have made extensive use
- of the inner structure, e.g., of lmer() results, will have to depend on
- lme4.0 until their code can be adapted.
+ This is the implementation of lme4 available on CRAN and developed up to 2011.
+ It has been renamed to lme4.0, and is now deprecated in favor of the new
+ lme4 package, for everything new.
+ For reproducibility of past research and data analysis, lme4.0 is kept
+ available. For the time being, code and other packages who have made
+ extensive use of the inner structure, e.g., of lmer() results, will have
+ to depend on lme4.0 until their code can be adapted.
Author: Douglas Bates <bates at stat.wisc.edu>,
Martin Maechler <maechler at R-project.org> and
Ben Bolker <bolker at mcmaster.ca>
Modified: pkg/lme4.0/man/convert_old_lme4.Rd
===================================================================
--- pkg/lme4.0/man/convert_old_lme4.Rd 2013-08-09 11:18:57 UTC (rev 1831)
+++ pkg/lme4.0/man/convert_old_lme4.Rd 2013-08-09 11:50:33 UTC (rev 1832)
@@ -1,35 +1,33 @@
\name{convert_old_lme4}
\alias{convert_old_lme4}
-\title{
- Convert old lme4 objects to lme4.0
-}
+\title{Convert Old-lme4 Objects to lme4.0 Ones}
\description{
- Given a fitted model created by the old (<= 0.999375-42) \code{lme4} package,
- convert it to be usable with the \code{lme4.0} package
+ Given a fitted model created by the old (<= 0.999999-2) \pkg{lme4} package,
+ convert it to be usable with the \pkg{lme4.0} package.
}
\usage{
convert_old_lme4(x)
}
\arguments{
- \item{x}{
- A fitted model from \code{lme4} (of class \code{mer})
+ \item{x}{fitted model from \pkg{lme4} (of class \code{\linkS4class{mer}}).}
}
-}
\details{
The function simply manipulates the \code{package} attribute of
- the object's class to allow \code{lme4.0} to recognize it.
+ the object's \code{\link{class}} to allow \pkg{lme4.0} to recognize it.
}
\value{
- A \code{mer} object usable by \code{lme4.0}
+ A \code{\linkS4class{mer}} object usable by \pkg{lme4.0}.
}
\author{
Ben Bolker
}
\examples{
## an example file containing old mer objects
-(L <- load(system.file("old_lme4_save.RData",package="lme4.0")))
-convert_old_lme4(fm1)
-convert_old_lme4(gm1)
+(load(system.file("old_lme4_save.RData", package="lme4.0")))
+validObject(fm2 <- convert_old_lme4(fm1)); fm2
+validObject(gm2 <- convert_old_lme4(gm1)); gm2
+## they differ by package attribute only :
+stopifnot(all.equal(fm1, fm2, check.attributes=FALSE, tol=0))
}
\keyword{misc}
Modified: pkg/lme4.0/tests/lmer-1.R
===================================================================
--- pkg/lme4.0/tests/lmer-1.R 2013-08-09 11:18:57 UTC (rev 1831)
+++ pkg/lme4.0/tests/lmer-1.R 2013-08-09 11:50:33 UTC (rev 1832)
@@ -124,7 +124,7 @@
## discrepancies have occured at digit 140.64x;
## digits= doesn't handle it properly since other
## elements have smaller magnitudes
- round(c(unlist(VarCorr(M2.))),2)
+ round(c(unlist(VarCorr(M2.))),2)
options(op)
## summary(M2.)
M2 <- lmer (y ~ x + ( x | group))
@@ -155,7 +155,7 @@
var(tstDF$y) # == 2.5
## Now throws an error
try(f.oops <- lmer(y ~ 1 + (1|group), data = tstDF))
-## summary(f.oops) ## or print(Matrix:::formatVC(VarCorr(f.oops)), quote = FALSE)
+## summary(f.oops) ## or print(....formatVC(VarCorr(f.oops)), quote = FALSE)
## ...
## Groups Name Variance Std.Dev.
## group (Intercept) 1.81818 1.34840
Modified: pkg/lme4.0/tests/lmer-1.Rout.save
===================================================================
--- pkg/lme4.0/tests/lmer-1.Rout.save 2013-08-09 11:18:57 UTC (rev 1831)
+++ pkg/lme4.0/tests/lmer-1.Rout.save 2013-08-09 11:50:33 UTC (rev 1832)
@@ -1,15 +1,12 @@
-R Under development (unstable) (2012-12-14 r61321) -- "Unsuffered Consequences"
-Copyright (C) 2012 The R Foundation for Statistical Computing
-ISBN 3-900051-07-0
-Platform: i686-pc-linux-gnu (32-bit)
+R Under development (unstable) (2013-08-08 r63524) -- "Unsuffered Consequences"
+Copyright (C) 2013 The R Foundation for Statistical Computing
+Platform: x86_64-unknown-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
- Natural language support but running in an English locale
-
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
@@ -286,9 +283,9 @@
> has.coda <- require(coda)
Loading required package: coda
-Attaching package: ‘coda’
+Attaching package: 'coda'
-The following object is masked from ‘package:lme4.0’:
+The following object is masked from 'package:lme4.0':
HPDinterval
@@ -489,7 +486,7 @@
nt n p q s np LMM REML fTyp lTyp vTyp nest useSc
1 20 2 4 1 3 1 1 2 5 1 1 1
nAGQ verb mxit mxfn cvg
- 1 0 300 900 4
+ 1 0 300 900 5
Slot "fixef":
[,1]
@@ -531,10 +528,10 @@
[1] 2.5
> ## Now throws an error
> try(f.oops <- lmer(y ~ 1 + (1|group), data = tstDF))
-Error in function (fr, FL, start, REML, verbose) :
+Error in (function (fr, FL, start, REML, verbose) :
Number of levels of a grouping factor for the random effects
must be less than the number of observations
-> ## summary(f.oops) ## or print(Matrix:::formatVC(VarCorr(f.oops)), quote = FALSE)
+> ## summary(f.oops) ## or print(....formatVC(VarCorr(f.oops)), quote = FALSE)
> ## ...
> ## Groups Name Variance Std.Dev.
> ## group (Intercept) 1.81818 1.34840
@@ -643,8 +640,8 @@
> if(.unsafe.BLAS) rm(identical)
>
> cat('Time elapsed: ', proc.time(),'\n') # for ``statistical reasons''
-Time elapsed: 5.608 1.612 7.891 0 0.024
+Time elapsed: 4.589 0.153 5.227 0 0
>
> proc.time()
user system elapsed
- 5.608 1.636 7.892
+ 4.589 0.153 5.227
More information about the Lme4-commits
mailing list