[R-sig-ME] Fitting linear mixed-effects models

[Thierry Onkelinx]

Do you want a random effect for methionine source at the study level? That
could work with the alternative model you specified. However, that assumes
that you have multiple records for every combination of study and
methionine source. I would expect that you have only one record for each of
those combinations.

ir. Thierry Onkelinx
Statisticus / Statistician

Vlaamse Overheid / Government of Flanders
INSTITUUT VOOR NATUUR- EN BOSONDERZOEK / RESEARCH INSTITUTE FOR NATURE AND
FOREST
Team Biometrie & Kwaliteitszorg / Team Biometrics & Quality Assurance
thierry.onkelinx using inbo.be
Havenlaan 88 bus 73, 1000 Brussel
www.inbo.be

///////////////////////////////////////////////////////////////////////////////////////////
To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to say
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer does not
ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey
///////////////////////////////////////////////////////////////////////////////////////////

<https://www.inbo.be>


Op di 25 jan. 2022 om 23:57 schreef Vinícius Carneiro de Souza <
vinicius2042 using hotmail.com>:

> I am trying to fit a linear model using the lmer function from data
> collected from literature from multiple studies.
> The response variable is the average daily gain of swine and the predictor
> is the different methionine sources in the different diets, which is a
> factor with 4 levels (4 different methionine sources)
>
> My original model is below, which includes a random intercept for study
> effect:
>
> #Z_ADG_g is the average daily gain
> #MM_Type_met is the methionine source factor
> #CO_Intra_Trial is the publication ID
>
> ADGmod <- lmer(Z_ADG_g~MM_Type_met+(1|CO_Intra_Trial), data=ErmDat3,
> weight=ADG_wt, REML = FALSE)
>
> summary(ADGmod)
>
> I would like to look what would be the effect of considering that each
> methionine source tested has a different/separate intercept. I was reading
> a book chapter from Bates et al. and found a table with some syntaxes that
> could work to specifying different intercepts for each methionine source,
> but it is not working. The model still has only one intercept.
>
> I tried the following model:
>
> ADGmod <-
> lmer(Z_ADG_g~MM_Type_met+(1|CO_Intra_Trial)+(1|CO_Intra_Trial:MM_Type_met),
> data=ErmDat3, weight=ADG_wt, REML = FALSE)
>
> summary(ADGmod)
>
> Does anyone know if it is even possible what I am trying to do?
>
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models using r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>

	[[alternative HTML version deleted]]