Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Predict after Factormat

From   "David Doyle" <>
To   <>
Subject   st: Predict after Factormat
Date   Wed, 7 Nov 2012 10:28:10 -0000

Dear Stata List Users,

I am trying to run a factor analysis with missing data. Currently, I am
following the procedure for factor analysis with missing data outlined on
the IDRE website at UCLA, using maximum likelihood with the
expectation-maximization (EM) algorithm to estimate the factor analysis from
the covariance matrix: 

This works fine, but I am having trouble using ?predict? to generate a new
variable after the factor analysis. The help files state I need to use the
means() option after factormat, but I cannot come across an example of the
syntax, and lots of different attempts I have made have been unsuccessful.

Does anyone know what I need to do to run predict after factormat? What is
the correct command?

The commands in the do-file I am using are as follows:

count /*count total number of observations */
mi set mlong
mi register imputed varlis1-33
mi impute mvn varlist1-33, emonly

matrix cov_em = r(Sigma_em)

matrix list cov_em

factormat cov_em, n(*) fact(1) pcf

rotate, varimax


I wish to follow this with predict, but currently I get his message: 

(variable means assumed 0; use means() option of factormat for nonzero

Any help would be greatly appreciated.



Dr. David Doyle
Lecturer in Politics
Director of the PhD Programme
School of Law & Government
Dublin City University

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index