similar to: A question on REML in R

Dear All, I have a question concerning the computation of the value of the Restricted Maximum Likelihood (REML) function evaluated at a given set of parameter estimates from the Maximum likelihood (ML) value. Following the book of Fitzmaurice, Laird and Ware (2004) "Applied Longitudinal Analysis" pp101, the REML likelihood can be computed by multiplying the ML likleihood by the square

Hello listmembers, I've been thinking of using gls in the nlme package to test for serial correlation in my data set. I've simulated a sample data set and have found a large discrepancy in the results I get when using the default method REML vs. ML. The data set involves a response that is measured twice a day (once for each level of a treatment factor). In my simulated data set, I

Hi, please help!! I've been trying to fit variogram models using the REML method in the gstat package. Every time the Windows GUI crashes. For example library(gstat) data(meuse) x <- variogram(zinc ~ 1, ~x + y, meuse) v <- vgm(140000, "Sph", 800, nug = 10000) plot(x, model = fit.variogram(x, model = v, fit.method=5)) Other fit methods are non problematic (eg. fit.method=7

Hi, In glmmPQL in the MASS library, the function uses repeated calls to the function lme(), using ML. Does anyone know how you can change this to REML? I know that in lme(), the default is actually set to REML and you can also specify this as 'method=REML' or 'method'ML' but this isn't applicable to glmmPQL(). I'd appreciate any help or advice! Thanks, Emma

Sorry for the off-topic (non-R) post. Has anyone seen/tried this (from this week's NA-digest)? Andy ------------------------------------------------------- From: Joel Malard <JM.Malard at pnl.gov> Date: Sat, 01 May 2004 15:31:15 -0700 Subject: ACRE, Parallel Covariance Component Estimation Code A couple of people have asked recently for a copy of the parallel (restricted/residual)

Hi, I am trying to use glmmPQL package for Generalized linear mixed models. This package works by repeated calls to lme. lme uses by default REML method for estimation. Then, does glmmmPQL use REML too? In contrast, how can I change it? I have tried it, writing : method="REML", but the program says: invalid method REML. If somebody can answer me....thanks, Sonja

Dear All, I am wondering about the fitting negative binomial(NB) hurdle model with random effect using REML estimation method in R. We can fit regular hurdle model without random effect using ML method as following. hurdle(pkg).... But, I couldn't figure out how I can fit NB hurdle model with random effect using REML in R. Please give me a tip. Thank you so much. Sincerely, SK

Dear All, As you know, glmmADMB package use ML method for estimation. Is it possible to use REML estimation method for zero-inflated Poisson distribution? For ML method, poi_ML <- glmm.admb(los ~ psihigh + trt.mod + trt.high + psihigh*trt.mod + psihigh*trt.high + 1, random = ~1, group="site", family="poisson", data=edcap) summary(poi_ML) How can I control to use REML

Hi everyone, I have been using REML to derive intercepts and coeficients for each individual in a growth study. So the code is m2 <- lmer(change.wt ~ newwt+(newwt|id), data = grow) Calling coef(model.lmer) gives a matrix with this information which is what I want. However, as a test I looked at each individual on its own and used a simple linear regression to obtain the same information, then

Hi, I know that is not possible make a stepwise procedure using REML in R, I can use ML for this. For nested design it may be very dangerous due the difference in variance structure, mainly in a splitplot design. ML make significative variables that REML dont make. I read an article that is made a stepwise procedure using GENSTAT. from article: "Terms were dropped from a model in a

Hi, I've been using gamm4 to build GAMMs for exploring environmental influences on genetic ancestry. Things have gone well and I have 2 very straightforward questions: 1. I've used method=REML. Am I correct that this is an alternative method for estimating the smooth functions in GAMMs rather than GCV that is often used for GAMs? I've read up on REML and it makes sense, but I'm

Hi Greg, For quasi families I've used extended quasi-likelihood (see Mccullagh and Nelder, Generalized Linear Models 2nd ed, section 9.6) in place of the likelihood/quasi-likelihood in the expression for the (RE)ML score. I hadn't realised that this was possible before the paper was published. best, Simon ps. sorry for slow reply, the original message slipped through my filter for

Hi R experts, I am interested on the effects of two dietry compunds on the growth of chicks. Rather than extracting linear growth functions for each chick and using these in an analysis I thought using ReML might provide a neater and better way of doing this. (I have read the pdf vignette("MlmSoftRev") and "Fitting linear mixed models in R" by Douglas Bates but I am not

Hi, All,   My data collection is from 4 regions (a, b, c, d). Within each region, it has 2 or 3 units. Within each unit, it has measurement from about 25 sample site. I was trying to use lme function to discribe relationship between y and a few covariates. Both y and covariates were measured at the sample site level. My question is when I use exactlly the same model but choose different estimation

Dear all, I am planning to use nlme library for analysis of experiments in semiconductor industry. Currently I am using "lm" but plan to move to "lme" to handle within wafer / wafer-to-wafer and lot-to-lot variation correctly. So far everything is working well, but I have a fundamentel question: NLME offers "maximum likelihood" and "restricted maximum

Can you provide the summary(m2) results? > -----Original Message----- > From: Simon Pickett [mailto:S.Pickett at exeter.ac.uk] > Sent: Wednesday, August 16, 2006 7:14 AM > To: Doran, Harold > Cc: r-help at stat.math.ethz.ch > Subject: [SPAM] - RE: [R] REML with random slopes and random > intercepts giving strange results - Bayesian Filter detected spam > > Hi again,

hi I'm puzzled as to the relation between the REML score computed by gam and the formula (4) on p.4 here: http://opus.bath.ac.uk/22707/1/Wood_JRSSB_2011_73_1_3.pdf I'm ok with this for poisson, or for quasipoisson when phi=1. However, when phi differs from 1, I'm stuck. #simulate some data library(mgcv) set.seed(1) x1<-runif(500) x2<-rnorm(500)

Dear list, I was trying to create a VarClass for nlme to work with Fay-Herriot (FH) models. The idea was to create a modification of VarComb that instead of multiplying the variance functions made their sum (I called it varSum). After some fails etc... I found that the I was not getting the expected results because I needed to make sigma fixed. Trying to find how to make sigma fixed I run into

Hello everyone, I hope this is a fair enough question, but I don’t have access to a copy of Bates and Pinheiro. It is probably quite obvious but the answer might be of general interest. If I fit a fixed effect with an added quadratic term and then do it as an orthogonal polynomial using maximum likelihood I get the expected result- they have the same logLik.