

H0 imputation and type = random 

Message/Author 

Jon Heron posted on Thursday, October 16, 2014  8:03 am



Hi Bengt/Linda I'm attempting to impute from an H0 model consisting of a single covariate and a linear growth model. I'm using TSCORES/type=random to incorporate variation in age at response and this is preventing me from using the Bayes estimator. Your technical appendix (Imputations7) states that if Bayes is not used, this becomes an H1 model and therefore my specified model is being ignored. So, am I right in thinking that my only solution is to turn this into a longformat multilevel model problem? thanks, Jon 


Jon I think longformat twolevel H0 imputation is the way to go. You get exactly what you want that way. 

Jon Heron posted on Thursday, October 16, 2014  10:35 am



awesome, thanks Tihomir, I have a followup question arising from my afternoon spent playing around with this. In the version history on the website, under "Analysis Conditional on Covariates" the last paragraph discusses bringing covariates into the model as the ML approach to dealing with missingness in x but gives the impression that a different approach is needed when using Bayesian imputation. Say as part of a larger model, I have missingness in x, but auxiliary information z containing info about missing x, how do I build this in? regress x on z? covary x and z? clearly both render x dependent so perhaps it doesn't matter that much. thanks again, Jon 

Jon Heron posted on Thursday, October 23, 2014  8:12 am



Sorry, me again. I'm attempting some twolevel imputation to replicate the findings obtained using REALCOMImpute, a package developed by the multilevelmodellers here in the UK. Their final model is to predict literacy using a handful of covariates, and allowing for withinschool clustering. As one of these covariates suffers from missing data they have an initial step where they derive an imputation model for this covariate, using the other data as predictors, and again allowing for school level clustering. I've attempted to achieve this same objective by setting up an H0 model in Mplus. Whilst I can get this to work using the following (below, where X1 has missing data) and also using a simpler approach using type = basic (still with clustering), I am unable to turn my within model from simple covariances to a regression model. For instance, if I minic the realcom approach and go with "X1 on Y X2 X3;" I lose all the cases for which X1 is missing. cluster = school; usevariables = Y X1 X2 X3; within = Y X2 X3; between = ; Missing are all (9999) ; Analysis: Type = twolevel ; ESTIMATOR Bayes; Model: %WITHIN% X1 Y X2 with Y X2 X3; %BETWEEN% X1; In my eyes, what I currently have here is not really an H0 model. Am I right? What can I do? many thanks, Jon 


You can say %Within% X1 ON Y X2 X3; Y X2 X3; which would handle missing on Y X2 X3 as well as not deleting subjects with missing on X1. But regarding missing on X1, the regression slopes in the X1 regression are estimated using only those with X1 observations; subjects with missing on X1 contribute only to the estimation of the parameters in the marginal part of Y X2 X3. 

Jon Heron posted on Thursday, October 23, 2014  11:41 pm



Thanks Bengt, I have much still to learn 

Back to top 

