Spatial model selection with loo

[avehtari]

@manjago

For each one of these units I have eight covariates like % of unemployment, average years of schooling, etc. Our interest is just to estimate the effect of each of this covariates over the conditions.

If the covariates are not correlating, you can also look at the posterior distribution of the model with all covariates.

@manjago

I already read some of your articles and apparently, using CV or information criteria is not a good choice for this purposes, but I’m not clear about the alternatives.

They can be fine when comparing just a few models.

@Error when fitting a CAR model in brms

As a workaround, could one use the brms weight argument to add one made-up datapoint (i.e., population mean) per new location, and then apply zero weights to said datapoints? This could be very wrong, but it feels so right.

Sounds reasonable

@manjago

About the posterior predictive checks, if I use the regular command, for a continuos response, they look “to good to be true” nice, which supports your overfit statement I think.

Yes

@manjago

Besides the model selection issue, does all of these problems means that this model is bad or invalid?

Not necessarily. Spatial models are sometimes very flexible and require more care to assess.