[R-sig-ME] Implications of modeling residuals in multilevel models

[Simon Harmel]

Hello All,

I have a highly skewed dataset. But, my MODEL of choice below shows
drastically improved, normally distributed residuals (and predicted values)
compared to other models whose residuals are not modeled.

Three quick questions:

1- Is MODEL below assuming that my data come from a population that looks
normal once "X1_categorical" and "X2_numeric" are taken into account
as modeled in MODEL?

2- Do these normally distributed predictions work better for a subject
randomly drawn from a similarly skewed population with a
known "X1_categorical" and "X2_numeric"?

3- I think the distribution of residuals mirrors that of the data. If so,
is it correct to say MODEL below is actually **trimming** my highly skewed
data as if it was distributed as:
```
hist(resid(MODEL, type = "normalized"))
```

 MODEL <- nlme::lme(y ~ X1_categorical + X2_numeric ...,
         random = ~1| subject,
         data = data,
         correlation = corSymm(~1|subject),
         weights = varComb(varIdent(form = ~ 1 |  X1_categorical ),
                                          varPower(form = ~  X2_numeric )))

Thanks,
Simon

	[[alternative HTML version deleted]]