Thanks again Dr. Kingston! Another question - how would you obtain or calculate degrees of freedom for glmer as it is not provided in the output?
On Sun, Sep 18, 2016 at 1:54 PM, John Kingston <jkings...@linguist.umass.edu > wrote: > Dear Simirtpal, > > You need to use "glmer" not "lmer" to run such a model. > > Best, > John > > > On 2016-09-18 13:41, Simritpal Malhi wrote: > >> Hello, >> >> I am trying to run my error analysis using a logit mixed model. I have >> installed the lmer test package because I would like to report >> p-values. I have attached a sample of how my data file is set-up. >> >> e$correct <- as.factor(e$correct) >> >> erranalysis=lmer(correct~task*concrete+task*embodied+ >>> >> >> task*symbolic+(1|item)+(1|subject),data=e, >> >> family=binomial) >> >> I put the dependent variable as "correct" and I added >> "family=binomial" to specify that the "correct" dependent variable was >> coded as 1 if the participant had an error and 0 if the participant >> was correct. However, I am getting the following error message: >> >> Error in as(model, "merModLmerTest") : no method or >> >> default for coercing “glmerMod” to “merModLmerTes” >> >> In addition: Warning messages: >> >> 1: In lme4::lmer(formula = correct ~ task * concrete + >> >> task * embodied + : calling lmer with 'family' is >> >> deprecated; please use glmer() instead >> >> 2: In checkConv(attr(opt, "derivs"), opt$par, ctrl = >> >> control$checkConv, : Model failed to converge with >> >> max|grad| = 0.00205133 (tol= 0.001, component 1) >> >> Any help would be appreciated. Thank you for your time. >> > > -- > John Kingston > Professor > Linguistics Department > University of Massachusetts > Integrative Learning Center N412 > 650 N. Pleasant St. > Amherst, MA 01003 > 1-413-545-6833, fax -2792 > jkings...@linguist.umass.edu >
