Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: data file for use with sem()

From   John Antonakis <>
Subject   Re: st: data file for use with sem()
Date   Fri, 07 Dec 2012 16:35:13 +0100


Yes, it is possible to analyze summary data, which can be then estimated by maximum likelihood. See -help ssd-

For your interest, see also -help corr2data-, which can generate artificial data with a known correlational structure too.



Prof. John Antonakis
Faculty of Business and Economics
Department of Organizational Behavior
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

Associate Editor
The Leadership Quarterly

On 07.12.2012 14:59, Robert Long wrote:
Hello statlist

I am fairly new to Stata and completely new to the sem() function.

I have previously used MPlus, where it is common to have data files in a format like this:

79.75 0.97 81.96 109.16
  14.18 0.58 54.24 10.40
  0.34 1
  0.59 0.39 1
  0.38 0.13 0.29 1

where we have a row vector for the means of each variable, a row for their standard deviations, a lower triangular matrix for correlations, and the number of observations is input separately.

Is there a way to get Stata to handle this kind of input without having the simulate the data myself ?

Robert Long

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index