Displaying 20 results from an estimated 120 matches similar to: "identical results with PQL and Laplace options in lmer function (package lme4)"
2004 Jan 30
0
GLMM (lme4) vs. glmmPQL output (summary with lme4 revised)
This is a summary and extension of the thread
"GLMM (lme4) vs. glmmPQL output"
http://maths.newcastle.edu.au/~rking/R/help/04/01/0180.html
In the new revision (#Version: 0.4-7) of lme4 the standard
errors are close to those of the 4 other methods. Thanks to Douglas Bates,
Saikat DebRoy for the revision, and to G?ran Brostr?m who run a
simulation.
In response to my first posting, Prof.
2006 Nov 15
1
dynamic aggregation of many variables
Hi,
i have many variables for in example 4weeks and want to do
aggregations, like mean standard , deviation etc..
With mean it works but how i can calculate the standard deviation for
the 4weeks and for every ID.
many thanks & regards, christian
week1 <- grep("(_PRO_001)",names(dmx3),perl=T)
week1table <- subset(dmx3,select=c(ID,week1))
week2 <-
2007 Jul 23
3
Aggregate daily data into weekly sums
Dear Lest,
I have a two-variable data frame as follows (the time peirod of the
actual data set is 10 years):
Date Amount
1 6/1/2007 1
2 6/1/2007 1
3 6/4/2007 2
4 6/5/2007 2
5 6/11/2007 3
6 6/12/2007 3
7 6/12/2007 3
8 6/13/2007 3
9 6/13/2007 3
10 6/18/2007 4
11 6/18/2007 4
12 6/25/2007 5
13 6/28/2007 5
2000 Jan 04
0
Stepwise logistic discrimination - II
I apologise for writing again about the problem with using stepAIC +
multinom, but I think the reason why I had it in the first place is
perhaps there may be a bug in either stepAIC or multinom.
Just to repeat the problem, I have 126 variables and 99 cases. I don't
know if the large number of variables could be the problem. Of couse the
reason for doing a stepwise method is to reduce this
2007 Aug 20
1
Ask for functions to obtain partial R-square (squared partial correlation coefficients)
The partial R-square (or coefficient of partial determination, or
squared partial correlation coefficients) measures the marginal
contribution of one explanatory variable when all others are already
included in multiple linear regression model.
The following link has very clear explanations on partial and
semi-partial correlation:
http://www.psy.jhu.edu/~ashelton/courses/stats315/week2.pdf
In
2008 Dec 06
1
Questions on the results from glmmPQL(MASS)
Dear Rusers,
I have used R,S-PLUS and SAS to analyze the sample data "bacteria" in
MASS package. Their results are listed below.
I have three questions, anybody can give me possible answers?
Q1:From the results, we see that R get 'NAs'for AIC,BIC and logLik, while
S-PLUS8.0 gave the exact values for them. Why? I had thought that R should
give the same results as SPLUS here.
2010 Jun 18
0
pcse package - is it OK to use it when my regression is weighted by each subgroup's mean
Hello!
Just would like to make sure I am not doing something wrong.
I am running an OLS regression. I have several subgroups in the data
set (locations) - and in each location I have weekly data for 2 years
- on my DV and on all predictors. Looks like this:
location week DV Predictor1 Predictor 2
location1 week1 xxx xxxxxxx xxxxxxxxx
location1 week2 xxx xxxxxxx xxxxxxxxx
.
.
2010 Oct 03
1
Encoding problem in Rd file
Dear all,
I have a problem with an Rd file containing French accentuated
characters. I have uploaded the file at
http://filex.cirad.fr/get?k=cjW7lImMaNC6Ci2vX0H
I have declared
Encoding: latin1
in the package DESCRIPTION file
and I have added
\encoding{latin1}
in the header of the Rd file.
When I compile the package manual, I have LaTeX errors:
! Package inputenc Error: Unicode char \u8:?F
2003 Jun 17
1
probability values ?
Hello
I try to find probability values of some predictor combinations using
logistic reg. in response level.
Firstly I found coefficients by glm function.
Then I followed two ways to get probability values:
1- probility <- exp(X0+bX1+cX2+...)/((1+exp(X0+bX1+cX2+...))
2- probility <- predict(glm.obj,type="resp")
Should have these two given same result ?
if so, I did not have. Why
2010 Apr 07
1
finding weekly average...
Hi All,
I have a time series data with two continuous variables (say Var1 and Var2)
for 4 years (***not continuous, do have some breaks because of missing
data***). Something like this:
Date Var1 Var2
12/01/2004 7 0
12/01/2004 0 0
12/01/2004 0 7
12/01/2004 7 0
12/01/2004 0 7
12/01/2004 0 7
12/02/2004 0 0
...
I need to find out weekly average of var1 and var2, so that I end up with
data like:
2006 Feb 07
1
post-hoc comparisons following glmm
Dear R community,
I performed a generalized linear mixed model using glmmPQL (MASS
library) to analyse my data i.e : y is the response with a poisson
distribution, t and Trait are the independent variables which are
continuous and categorical (3 categories C, M and F) respectively, ind
is the random variable.
mydata<-glmmPQL(y~t+Trait,random=~1|ind,family=poisson,data=tab)
Do you think it
2009 Feb 15
1
GLMM, ML, PQL, lmer
Dear R community,
I have two questions regarding fitting GLMM using maximum likelihood method.
The first one arises from trying repeat an analysis in the Breslow and
Clayton 1993 JASA paper. Model 3 of the epileptic dataset has two random
effects, one subject specific, and one observation specific. Thus if we
count random effects, there are more parameters than observations. When I
try to run the
2008 Jul 06
2
Error: cannot use PQL when using lmer
> library(MASS)
> attach(bacteria)
> table(y)
y
n y
43 177
> y<-1*(y=="y")
> table(y,trt)
trt
y placebo drug drug+
0 12 18 13
1 84 44 49
> library(lme4)
> model1<-lmer(y~trt+(week|ID),family=binomial,method="PQL")
Error in match.arg(method, c("Laplace", "AGQ")) :
'arg' should be one of
2005 Nov 24
1
AIC in lmer when using PQL
I am analysing binomial data using a generalised mixed effects model. I
understand that if I use glmmPQL it is not appropriate to compare AIC
values to obtain a minimum adequate model.
I am assuming that this means it is also inappropriate to use AIC values
from lmer since, when analysing binomial data, lmer also uses PQL
methods. However, I wasn't sure so please could somebody clarify
2011 Dec 08
0
SVM performance using laplace kernel is too slow
I've created an SVM in R using the kernlab package, however it's running incredibly slow (20,000 predictions takes ~45 seconds on win64 R distribution). CPU is running at 25% and RAM utilization is a mere 17% ... it's not a hardware bottleneck. Similar calculations using data mining algorithms in SQL Server analysis services run about 40x faster.
Through trial and error, we
2010 Nov 24
0
Laplace Approximation
Does anyone have any R code that shows how to do a Laplace Approximation? I
know there are a variety of these numerical approximation algorithms and I'm
pretty open at this point, I'm just curious how it's approximated in R code.
I have seen some functions in packages, but I think they all call C code,
and am looking for an example in R only. Thanks.
--
View this message in
2003 Jun 23
0
Reliability analysis and Laplace factor functions
Is there some package out there that implements functions
for reliability analysis, especially for software reliability?
In particular, I'm looking for:
* Laplace factor (Cox & Lewis 1978)
* Goel-Okumoto fitting
Thanks in advance,
-Ekr
--
[Eric Rescorla ekr at rtfm.com]
2011 Oct 02
0
Multivariate Laplace density
Can anyone show how to calculate a multivariate Laplace density? Thanks.
--
View this message in context: http://r.789695.n4.nabble.com/Multivariate-Laplace-density-tp3864072p3864072.html
Sent from the R help mailing list archive at Nabble.com.
2010 Mar 11
1
Dicrete Laplace distribution
Hello,
<http://tolstoy.newcastle.edu.au/R/help/04/07/0312.html#0313qlink1> Could
anybody tell me how to generate discrete Laplacian distribution?
I need to sample uma discretised Laplacian density like this:
J( g -> g´) ~ exp (-lambda | g´ - g |) g in {0,…, gmax}
Thanks,
Nicolette
[[alternative HTML version deleted]]
2008 Nov 01
2
sampling from Laplace-Normal
Hi,
I have to draw samples from an asymmetric-Laplace-Normal distribution:
f(u|y, x, beta, phi, sigma, tau) \propto exp( - sum( ( abs(lo) +
(2*tau-1)*lo )/(2*sigma) ) - 0.5/phi*u^2), where lo = (y - x*beta) and
y=(y_1, ..., y_n), x=(x_1, ..., x_n)
-- sorry for this huge formula --
A WinBUGS Gibbs sampler and the HI package arms sampler were used with the
same initial data for all parameters. I