I have a dataset consisting of 11 items of binary data (0/1) that will be the basis for my dependent variable. There are 240 observations collected by means of a survey. Since the data is binary, the CFA is run based on summary statistics (SSD) and using polychoric correlations. See code below (as also previously supplied in this forum):
----
local thevars ..."list of variables goes here"...
polychoric `thevars'
mat polychR = r(R)
forvalues i=1/`: word count `thevars' ' {
forvalues j=1/`i' {
local setcor `setcor' `=polychR[`i',`j']'
}
if `i' < `: word count `thevars' ' local setcor `setcor' \
}
local N = _N
clear
ssd init `thevars'
ssd set obs `N'
ssd set cor `setcor'
..."sem or factormat with options start here..."
----
This code has provided me with a good model, the problems I have is with figuring out how to be able to predict factor-scores for my observations. As the Stata-memory only holds summary statistics after the sem-command, I can not run “predict” as I could have if based on the raw data. How should I proceed in order to predict factor-scores for my observations?
Related Posts with Predicting factorscores after conducting a CFA based on summary statistics
Average Marginal effects for a multilevel modelHi, Please, I wanted to know the appropriateness of deriving marginal effects from a multilevel mod…
problem installing using the ssc commandI am using Stata/MC 16.1 on Windows 10 (also had the same problem using Ubuntu Linux 18.04). I have…
What does 1.009e-12 mean?What does 1.009e-12 mean? Can you show it in a decimal expression? How to transfer it to decimal ex…
wbopendata query error 23Hi all, I've been running into the following error for several days now: wbopendata query erro…
How to colour bars in a histogram or graph barHi there, I have been trying to colour individual bars in a histogram or graph bar with percentages…
Subscribe to:
Post Comments (Atom)
0 Response to Predicting factorscores after conducting a CFA based on summary statistics
Post a Comment