CODEWITHSUNDEEP
rlme4
Nadineskii
Nadineskii

Reputation: 31

Why is my glmer model in R taking so long to run?

I had previously been using simple stats in Statistica, but required R for my masters research. I am trying to run the following code to test for any significant interactions, and it is just running forever. If I simplify the model by taking month out, then it runs, but biologically it makes sense that month is significant so I would really like this to run including month as a factor. Once I run the model, the stop sign in R studio just stays present for hours, what could be the reason for this? Like I said I'm very new and it has been really difficult to learn this on my own. I am working with presence/absence data (as %) which I do cbind as my dependent variable. SO far this is what my coad looks like:

library(car)
library(languageR)
library(AICcmodavg)
library(lme4)

Scat <- read.csv("Scat2.csv", header=T)

attach(Scat)

names(Scat)

y <- cbind(Present,Absent)

ScatData <- glmer(y ~ Estate * Species * Month * Content * (1|Site) + Min + Max,family=binomial)

summary(ScatData)

Once I get to running the actual model, I don't even get to do the summary because R is not done computing the results of the actual model. I ran the model for approximately 4 hours, and when I clicked on the stop sign, I received this message:

Warning message: In (function (fn, par, lower = rep.int(-Inf, n), upper = rep.int(Inf, : failure to converge in 10000 evaluations

I would really appreciate some input on this matter.

Upvotes: 3

Views: 5696

Answers (1)

hartshoj
hartshoj

Reputation: 1202

You have a few problems with your model specification. Your model

y ~ Estate * Species * Month * Content * (1|Site) + Min + Max

is asking for all the main effects and interactions of estate, species, month, content, and site, which is incredibly complex.

Also, you have specified site as a random effect and asked for its interaction with fixed effects. I'm not sure whether that's possible, but it certainly seems wrong. You should decide whether you want site to be a fixed effect or a random effect.

If you post a minimal replicable example, I can give more specific advice.

Upvotes: 3

Related Questions