Linear mixed effect models in Jamovi | 3 | Factor coding, scaling, & residual normality

In this video, I will demonstrate how to fit a linear mixed effect model.
I will discuss:
What is a mixed effect model?
Fixed effects
Random effects: grouping or clustering factor
The intercept
The slope
Organizing data
Model fitting and model comparison: AIC, BIC, LL
Checking the assumptions
Variance components: variance and mean
Intra-class correlation (ICC)

[@christophermawhinney6713]

These 3 related videos explaining LMM jamovi outputs are fantastic...thanks for taking the time to explain to us mere mortals.

[@vicentemirallesliborio3573]

superhelpful! thank you so much. looking forward to watch any video you'll upload.

[@vicentemirallesliborio3573]

Hello again! I was wondering if you could help me with two questions related to this topic:
- Choosing a different scale for the dependent variable in the 'covariates scaling' menu, is it the same as choosing a link function in a generalized mixed model?
- And this same concept, but moving to a more practical level: choosing a generalized mixed model with a Gaussian distribution and a 'log' link function, would it be the same as a linear mixed model with a 'log' scale in your dependent variable? As far as I am concerned, I do not think so, since I tried both and I obtained different p-values for fixed factors.
Thank you a lot in advance,
Regards,

[@VahidAryadoust]

A quick response: no, these are different concepts, and generalized linear model is a different approach to LMEMs.

[@vicentemirallesliborio3573]

@@VahidAryadoust thank you vahid!