www.cmm.bristol.ac.uk/forum

Dear Lorraine
If the multiple imputation has done its job properly, i.e. te assumptions are reasonable (MAR) then you dont need to have the same no of records for null modle and imputed model in order to study the relative amounts ofvariance explained in both cases since you should be getting ...

That's right. If you have a binary response you need to move to a multivariate model. see
Barbosa and Goldstein (2000), Quality and quantity, 34, pp323-330

As I understand it, your model is a repeated measures model where you have some responses missing for some individuals at some occasions (months). If you just set this up as a 2-level model then there is typically no problem since the level 2 units (individuals) just have different numbers of level ...

If you only have weights at 1 level then leave the weights at the other level as 'equal'. To use standardised weights just specify the weights column and check 'use standardised weights' in the menu box.
Harvey

My view would be that all associated covariances should be constrained to zero also.
harvey

What you suggest seems quite sensible to me and would apply whether you used IGlS or MCMC estimation. There is an analogous procedure for ordered data. You also might consider partitioning the covariances (correlations).

You can impute several variables at a time - but it does not use chained equations. Explanatory variables in imputation model must have no missing values - if any have make them responses in imputation model.

If I understand your model it seems to me that what you call the level 1 classification (am/pm) is actually a predictor variable and if you treat it as such then your analysis is straightforward, isn't it?

Ignore previous post - should have read that it is inappropriate to predict a level 2 using a level 1 variable - this seems implicitly what is happening in your model.

It typically doesn't make sense to predict a level 1 outcome using something defined at level 2. It can be specified but what happens is that such a model effectively induces dependencies among level 1 residuals. Also not easy to interpret.
Harvey Goldstein