Issue with boundary (singular) fit: see ?isSingular

Hi again,

Just an update. I received this reply about the strange warning (Check model convergence: log-likelihood estimates lead to negative Chi-squared!)

Yes, the convergence issues will lead to non-observable Chi-squared. If you remove those random components with variance close to 0, it should help.



On Mon, 4 Oct 2021 at 15:23, Sasha Vasconcelos <sasha.m.vasconcelos at gmail.com> wrote:

If there are only two years, it's not surprising that you'll get
estimates of zero variance for (1|Year).  I would probably make Year a
fixed effect.
I also tried that, leaving only Point as a random effect. But I still get the singularity warning. Could it be that the sample size is simply too small to handle any sort of random structure..?


   I can't find this warning message anywhere, even in the development
branch of piecewiseSEM:

https://github.com/jslefche/piecewiseSEM/search?q=convergence

??

 I also haven't been able to find anything about that warning message anywhere, so I've posted this same question to

jslefche/piecewiseSEM on github and am hoping for an answer soon.



On Mon, 4 Oct 2021 at 14:16, Ben Bolker <bbolker at gmail.com> wrote:

On 10/4/21 10:05 AM, Sasha Vasconcelos wrote:

Hi,

I'm running a piecewise SEM with 3 component models:

lmer(response variable1 ~ predictors + (1|Point) + (1|Year), input_table)

glmer(response variable2 ~ predictors + (1| Point) + (1|Year), family =
"binomial", input_table)

glmer(response variable3 ~ predictors + (1| Point) + (1|Year), family =
"binomial", input_table)

Because sampling involved visiting 18 points in spring of 2018 and again in
spring of 2019, I specified samping point and year as random effects.

   If there are only two years, it's not surprising that you'll get
estimates of zero variance for (1|Year).  I would probably make Year a
fixed effect.

When I run the model, this warning message appears:
Check model convergence: log-likelihood estimates lead to negative
Chi-squared!

   I can't find this warning message anywhere, even in the development
branch of piecewiseSEM:

https://github.com/jslefche/piecewiseSEM/search?q=convergence

??

This message also appears:
boundary (singular) fit: see ?isSingular

 From what I've read about the second message, it could be due to random
effect variance estimates of zero. I checked and this happens in the 1st
and 3rd component models. In the 1st model "Point" has zero variance, and
in the 3rd model "Year" has zero variance.

My first question is (and I apologize in advance if this is silly to ask)
whether this means that there's not really an effect coming from Point in
component model 1 and from Year in component model 2? If so, would it be
possible to remove those random effects to end up with:

lmer(Response variable1 ~ Predictors + (1|Year), input_table)

glmer(Response variable2 ~Predictors + (1| Point) + (1|Year), family =
"binomial", input_table)

glmer(Response variable3 ~ Predictors + (1| Point), family = "binomial",
input_table)

   Seems reasonable.

My second question is whether the warning "Check model convergence:
log-likelihood estimates lead to negative Chi-squared!" is related to these
singularity issues?

Oh and I am using the development version of the piecewise SEM package
installed using devtools. This is because this version provides additional
standardized coefficients for GLMM.


Thanks!

--
Dr. Benjamin Bolker
Professor, Mathematics & Statistics and Biology, McMaster University
Director, School of Computational Science and Engineering
Graduate chair, Mathematics & Statistics

--
Sasha Vasconcelos

PhD student
CIBIO/InBIO, Research Center in Biodiversity and Genetic Resources, Associate Laboratory
Instituto Superior de Agronomia
Tapada da Ajuda
1349-017 Lisbon, Portugal

ResearchGate
ResearcherID

--
Sasha Vasconcelos

PhD student
CIBIO/InBIO, Research Center in Biodiversity and Genetic Resources, Associate Laboratory
Instituto Superior de Agronomia
Tapada da Ajuda
1349-017 Lisbon, Portugal

ResearchGate
ResearcherID