similar to: help with constrOptim function

Hello. Please excuse this off-topic request, but I know that the question has been debated in summary form on this list a number of times. I would find a paper that lays out the advantages and disadvantages of using different types of SS in the context of unbalanced data in ANOVA, regression and ANCOVA, especially including the use of different types of contrasts and the meaning of the

Hello. I have to fit a mixed model from a repeated measures split-plot experiment in which the response variable is binary. This requires a generalised linear mixed model in which I can specify a binomial distribution. I can’t find the appropriate package in R. I have looked at glmmML, but it doesn’t seem to allow any mixed structure beyond a simple 2-level one. Can anyone point me to the

Hello. I want to plot the distribution of a continuous variable (y) in each of two groups on the same graph as histograms. I suppose one could call this a 2-d histogram? Can this be done in R? Here is a typical data.set: y group 1.2 1 3.3 1 2.4 2 5.7 1 0.2 2 etc. Bill Shipley Subject Matter Editor, Ecology North American Editor, Annals of

To avoid angry replies, let me first say that I know that the use of Type III sums of squares is controversial, and that some statisticians recommend instead that significance be judged using the non-marginal terms in the ANOVA. However, given that type III SS is also demanded by some… is there a function (equivalent to drop1 for lm) to obtain type III sums of squares for mixed models using the

Hello. I am about to do a rather complicated analysis and am not sure how to do it. The experiment has a split-plot design and also repeated measures. Both of these complications require one to define an error term and it seems that one cannot specify two such terms. The split-plot command is: aov(y~covariates +A*B+Error(C), data=) where A and B are the fixed effects and C is the

Hello. Slope estimates in lme are shrinkage estimates which pull the OLS slope estimates towards the population estimates, the degree of which depends on the group sample size and the distance between the group-based estimate and the overall population estimate. Although these shrinkage estimates as said to be more precise with respect to the true values, they are also biased. So there is a

Hello. I am trying to fit a non-rectangular hyperbola function to data of photosynthetic rate vs. light intensity. There are 4 parameters that have to be estimated. I find the nls function very difficult to use because it often fails to converge and then gives out cryptic error messages. I have tried playing with the control parameters but this does not always help. Is there another

Hello. I want to estimate the predicted values and standard errors of Y=f(t) and its first derivative at each unique value of t using the smooth.spline function. However, the data (plant growth as a function of time) show substantial heterogeneity of variance since the variance of plant mass increases over time. What is the consequence of such heterogeneity of variance in terms of bias in the

Hello. I am sorry for posting a (seemingly) simple question, but I have just spent 2 hours trying to find the answer, without success. I want to make a histogram with conditioning on a factor, using Trellis graphics. However, I do not want any colours (only black and white) either in the histograms or in the strip. There must be some simple argument but I can’t find it. Here is my code so

Hello. I am trying to determine whether I should be using ML or REML methods to estimate a linear mixed model. In the book by Pinheiro & Bates (Mixed-effects models in S and S-PLUS, page 76) they state that one difference between REML and ML is that « LME models with different fixed-effects structures fit using REML cannot be compared on the basis of their restricted likelihoods. In

Hello. I want to specify a diagonal structure for the covariance matrix of random effects in the lme() function. Here is the call before I specify a diagonal structure: > fit2<-lme(Ln.rgr~I(Ln.nar-log(0.0011)),data=meta.analysis, + random=~1+I(Ln.nar-log(0.0011)|STUDY.CODE,na.action=na.omit) and this works fine. Now, I want to fix the covariance between the between-groups slopes

Hello. I am using the nonlinear least squares function (nls). The function that I am trying to fit seems to be very sensitive to the starting values and, if these are not chosen properly, the nls function stops and gives an error message: Error in numericDeriv(form[[3]], names(ind), env) : Missing value or an Infinity produced when evaluating the model In addition: Warning

Hello. Following pages 342-347 of Pinheiro & Bates, I am trying to write a self-starting nonlinear function (a non-rectagular hyperbola) to be used in nonlinear least squares regression (and eventually for a mixed model). When I use the getInitial function for my self-starting function I get the following error message: > getInitial(photo~NRhyperbola(Irr,theta,Am,alpha,Rd),dat) Error

Hello. I am trying to understand the syntax of the nonlinear least squares function (nls) when the function definition is made outside of the call. Here is the context. 1. If I specify the following command, it works fine: > fit2<-nls( + A~Am*(1-exp(-alpha*(I-LCP))),data=dat1, + start=list(Am=3.6,alpha=0.01,LCP=20)) 2. Now, I want to be able to specify the function definition

Hello. I cannot find out how to extract the residuals from a mixed model using the lmer function. Can someone help? Bill Shipley North American Editor, Annals of Botany Editor, "Population and Community Biology" series, Springer Publishing Département de biologie, Université de Sherbrooke, Sherbrooke (Québec) J1K 2R1 CANADA Bill.Shipley@USherbrooke.ca

Hello. I am having trouble downloading the lme4 package from the CRAN site. The error is: > local({a <- CRAN.packages() + install.packages(select.list(a[,1],,TRUE), .libPaths()[1], available=a, dependencies=TRUE)}) trying URL `http://cran.r-project.org/bin/windows/contrib/2.0/PACKAGES' Content type `text/plain; charset=iso-8859-1' length 26129 bytes opened URL downloaded 25Kb

Hello. I have come across a curious result that I cannot explain. Hopefully, someone can explain this. I am doing a 1-way ANOVA with 6 groups (example: summary(aov(y~A)) with A having 6 levels). I get an F of 0.899 with 5 and 15 df (p=0.51). I then do the same analysis but using data only corresponding to groups 5 and 6. This is, of course, equivalent to a t-test. I now get an F of 142.3

I am having difficulty understanding the syntax of the nlme() function for nonlinear mixed models. The data frame is called Marouane.chlorophyll. The model involves a dependent variable (Absorb) and an independent variable (Ch.surf), which are both numeric variables in the data frame. The data are hierarchically grouped as Espece, Plante nested within Espece, and Feuille nested within Plante

Hello. I have searched the archives but have not found anything. I need to solve a constrained optimisation problem for a nonlinear function (“maximum entropy formalism”). Specifically, Optimise: -1*SUM(p_ilog(p_i)) for a vector p_i of probabilities, conditional on a series of constraints of the form: SUM(T_i*p_i)=k_i for given values of T_i and k_i (these are constraints on

Earlier, I had posted the following question to the group : > Hello. I have come across a curious result that I cannot explain. > Hopefully, someone can explain this. I am doing a 1-way ANOVA with 6 > groups (example: summary(aov(y~A)) with A having 6 levels). I get an > F of 0.899 with 5 and 15 df (p=0.51). I then do the same analysis but > using data only