Implications of type = missing PreviousNext
Mplus Discussion > Missing Data Modeling >
Message/Author
 Tom posted on Thursday, December 29, 2005 - 1:47 pm
In comparing some models that I have run, when I include type = missing, the sign of some factor loadings from latent variables change.

Any idea what may be going on?

Thanks.
 bmuthen posted on Thursday, December 29, 2005 - 6:17 pm
Type = Missing is the preferred option with missing data because it leads to using all available data. In contrast, if you don't say Type = Missing you get listwise deletion (note the sample size change).
 Tom posted on Thursday, December 29, 2005 - 8:27 pm
I appreciate the contrast in sample size. Using type = missing, the sample size is 891 and without type = missing, the sample size is 774.

It is striking that the difference in t-scores would change rather dramatically with those cases deleted.

Would there be a difference if the indicators are categorical (vs. continuous)?
 Linda K. Muthen posted on Friday, December 30, 2005 - 8:23 am
It sounds like you have very selective missingness if the results from listwise deletion and TYPE=MISSING; are so different. This can happen for catgegorical or continuous indicators.
 Joseph posted on Tuesday, February 21, 2006 - 10:34 am
Dear Linda,
I am runing SEM using Mplus. If TYPE=MISSING in the ANALYSIS command and STANDARDIZED in the OUTPUT command were used at the same time, the results only provided "Estimates" (no S.E., Est./S.E., Std, StdYX). Any solution? Thanks.
 Linda K. Muthen posted on Tuesday, February 21, 2006 - 1:10 pm
I would need to see your output There is no reason you cannot use TYPE=MISSING with STANDARDIZED. Please send the output and your license number to support@statmodel.com.
 Joseph posted on Tuesday, February 21, 2006 - 3:41 pm
Thanks - Linda. It may be due to the divergent mode. It worked out after I modified the model. Sorry for this. Thanks.
 David Buitenweg posted on Tuesday, March 17, 2015 - 4:48 am
Hi,
I am a little confused about type =missing in Mplus. Does it tell Mplus to use an estimator viable when some data is missing, or does it impute data as well?
 Linda K. Muthen posted on Tuesday, March 17, 2015 - 5:20 am
The default in Mplus is to use all available information. For maximum likelihood estimators, this is often referred to as FIML. See the Little and Rubin book referenced in the user's guide. For weighted least squares, it is pairwise present. Mplus also can do multiple imputation.
 David Buitenweg posted on Tuesday, March 17, 2015 - 6:11 am
Hi Linda,

Thanks for the reply! I am performing mixture analysis, using EM rather than ML. Does Mplus use FIML for missing data in this case as well?
 Bengt O. Muthen posted on Tuesday, March 17, 2015 - 8:00 am
Yes.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: