[R-sig-ME] Issue with boundary (singular) fit: see ?isSingular

[Sasha Vasconcelos]

It was from Jon Lefcheck. Yes piecewiseSEM is the only package I'm using.

Sasha

On Mon, 4 Oct 2021 at 20:12, Ben Bolker <bbolker using gmail.com> wrote:

>   From whom? Is piecewiseSEM really the only package you're using? It
> disconcerts me that I can't locate the error message in any source
> code I've found so far.
>
> On Mon, Oct 4, 2021 at 3:04 PM Sasha Vasconcelos
> <sasha.m.vasconcelos using gmail.com> wrote:
> >
> > 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 using 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 using 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
> >>>
> >>> _______________________________________________
> >>> R-sig-mixed-models using r-project.org mailing list
> >>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
> >>
> >>
> >>
> >> --
> >> 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
> >
>


-- 
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 <https://www.researchgate.net/profile/Sasha_Vasconcelos>
ResearcherID
<https://publons.com/researcher/2593829/sasha-vasconcelos/publications/>

	[[alternative HTML version deleted]]