Outliers in CFA PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Rules Comm posted on Saturday, July 02, 2011 - 11:02 am
Professors,

I am coping with outliers in CFA. There are 7 outliers in a 400 cases dataset. I do not want to delete them because they are meaningful. Could you suggest any way that I can deal with them? I have tried to search in this web and other webs. But I did not find anything related to CFA and outliers. Thanks.
 Linda K. Muthen posted on Sunday, July 03, 2011 - 10:02 am
You would probably get a larger response to a general question like this on a general discussion forum like SEMNET.
 Peter Taylor posted on Wednesday, August 06, 2014 - 7:58 am
I just wanted to check if it is still appropriate to use Cook's distances to check for outliers in a CFA model with categorical (ordinal) indicators - is the interpretation of Cook's distances the same in this context? Thanks
 Bengt O. Muthen posted on Wednesday, August 06, 2014 - 11:57 am
Not sure how widely accepted Cook's is for categorical outcomes. I would use Loglikelihood outliers, obtained by ML.
 Peter Taylor posted on Thursday, August 07, 2014 - 12:34 am
Thanks for your help. Just to clarify then, would loglikelihood outliers still be interpretable with WLSMV estimation (as ordinal data)? Also, I am less familiar with loglikelihood outliers, are there any rules of thumb about what constitutes an outlier, or is it more a case of looking for points that are far out from the tail of the distribution? Many thanks
 Linda K. Muthen posted on Thursday, August 07, 2014 - 9:23 am
Weighted least squares estimators do not have loglikelihoods. You would need to use maximum likelihood if you want to look at the loglikelihoods.
 Peter Taylor posted on Monday, August 11, 2014 - 2:14 am
In that case is there a way of identifying outliers in a CFA with ordinal indicators and WLSMV estimation? Or is it a case of estimating the model with ML (and tresting the indicators as continuous)? Thanks
 Linda K. Muthen posted on Monday, August 11, 2014 - 6:15 am
You can estimate the model with ML and treat the indicators as categorical.
 Peter Taylor posted on Tuesday, August 12, 2014 - 1:06 am
One last question, if I did want to stick to WLSMV estimation are there any means of identifying outliers in Mplus that you would recommend?
 Bengt O. Muthen posted on Tuesday, August 12, 2014 - 9:31 am
Not sure I would. Outliers are better chased by ML.
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: