Search Archives

Dear all, A reviewer has asked me to apply a correction to multiple comparisons conducted for a logistic mixed effect regression with binary outcome. The model is: glmer(outcome ~ factor1 * factor2 + (1|RE1) + (1|RE2), family =binomial, data = data) where...

Dear all, I am now for the first time needing to run ME analyses with likert-scale-type data obtained from acceptability judgments in a linguistic experiment. The responses range between 1 and 5, are ordered, and will involve continuous...

Dear Joao and Phillip, Thank you so much for your suggestions. Please keep them coming everyone ? Francesco On Sun, 19 Mar 2023 at 16:17, Phillip Alday <me at phillipalday.com> wrote: > See also > > https://doingbayesiandataanalysis.blogspot.com/2018/09...

Sema, E is just a computer way of saying 0. For the purpose of statistical analysis, if you can't compute a calculation with E values (i.e. 0), substitute all E values with a usable constant, say 50. I...

Dear all, I'm trying to report my analysis replicating the method in the following papers: Cai, Pickering, and Branigan (2012). Mapping concepts to syntax: Evidence from structural priming in Mandarin Chinese. Journal of Memory and Language 66 (2012) 833...

Hello All, I am trying to run a type III Anova test on a zero-inflation poisson model with count data to obtain stats for main effects. In other words, I would like the output to include the df, Chisq...

One more question regarding the interpretation of interactions. I am having difficulty finding information on how to obtain a specific contrast in a 3-way interaction of three categorical variables, syntax (levels s and of), animacy (levels +AN -AN and...

Dear all, I have more of a theoretical than practical question for you. The model I am using has two IVs, group (3 levels) and task (2 levels), and a categorical DV (correct versus incorrect), hence logistic regression. Random effects...

Hello Thierry, Unfortunately that doesn't seem to make any difference. The result is the same: *Group2 -1.3802 0.6907 -1.998 0.045681 * * I paste the output below. #create a new dummy variable recoding RESP# > masterPT$Correct <- 0...

Dear all, Apologies for cross-posting if you are also part of R-ling-lang. I am struggling to understand my results and would appreciate some advice on a matter that has more to do with understanding logistic regression outputs...

Dear all, A journal has asked that I determine the effect sizes for a series of dummy-coded contrasts from the following ME model: RT ~ Group * Grammaticality + (1 + Grammaticality | Participant) + (1 + Group | item) Here RT is my continuous outcome variable...

For some reason the silly bugger didn't past the full command: > revanaA<- bglmer(Correct~Syntax*Animacy*Prof.group.2+(1|Part.name)+(1|Item), data = revana, family = binomial, fixef.prior = normal(cov = diag(9,16))) fixed-effect model matrix...

Many thanks Ben, but I tried that already: > revanaA<- bglmer(Correct~Syntax*Animacy*Prof.group.2+(1|Part.name)+(1|Item), data = revana, family = binomial, fixef.prior = normal(cov = diag(9,16))) fixed-effect model matrix is rank deficient so...

After giving up on a glmer for my data, I remembered a post by Roger Levy suggesting to try the use non mixed effects glm when one of the cells in a matrix is zero. To put this into perspective...

Hello Tom, Thank you so much for pitching in. I haven't touched the levels for group so the ref level is L1-L2 as far as I can see. > contrasts(masterPT$Group) 2 L1 0 L2 1 What seems...

I wonder if anyone can help with the separation problem originally solved by Ben Bolker (see thread). The model and fitting I used previously was trial<-bglmer(Correct ~ Syntax.Semantics, data = trialglm, family = binomial, fixef.prior = normal(cov = diag(9...

Hello again, if I understand you correctly, you're trying to get R to tell you what the p value should be. This is the result of using the commands you indicated: > options(error=recover) > if (length(cov) == p) {cov...

Yes. An ANOVA with my final bglmer model yields: > anova(recallmodel4x6a) Analysis of Variance Table Df Sum Sq Mean Sq F value syntax12 1 1.7670 1.7670 1.7670 animacy12 1 3.4036 3.4036 3.4036 group123 2...

Many thanks to both. The approaches you suggest (and others online) help one deal with the separation problem but don't offer any specific advice as to how getting a valid p coefficient when comparing two levels of the model...

John, I tried the Anova() function in the car package implemented with contr.sum() but it doesn't produce beta, SE, z, and p. To be more precise, R requires that either the F or Chi sq statistic be used...