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: Creating an index

From   Nick Cox <>
Subject   Re: st: Creating an index
Date   Thu, 17 May 2012 00:07:08 +0100

-sem- was added in Stata 12. See

The Statalist FAQ advises -- at --

"The current version of Stata is 12.1. Please specify if you are using
an earlier version; otherwise, the answer to your question is likely
to refer to commands or features unavailable to you."


On Wed, May 16, 2012 at 9:12 PM, Ozgur Ozdemir <> wrote:
> Hi Maarten,
> thanks for your help. I would like to try a SEM model however I have version 10. Is it possible to do SEM in version 10 if so, how can I find step by step instructions?
>> From:

>> On Tue, May 15, 2012 at 10:53 PM, Ozgur Ozdemir wrote:
>> > it seems, I need to use
>> > sheaf coefficient like technique.  "Combining information from multiple variables using models for casual indicators" explains how several variables can be grouped and used as an independent variable but not sure how I can use the new variable as a dependent variable in a test ?
>> > in your example, if I want to use the family socio economic status as dependent variable in a regression, first I need to create the index and calculate the actual socio economic values.
>> You can use the -post- option in -sheafcoef- and than use -predict- to
>> predict the latent variable.
>> *---------------------- begin example -----------------------------
>> sysuse nlsw88, clear
>> tab occupation, gen(occ)
>> gen ttl_exp2 = ttl_exp*ttl_exp
>> glm wage occ2-occ13 married never_married grade ttl_exp*, link(log)
>> // with the post option it turns -sheafcoef- into a regular
>> // estimation command,
>> sheafcoef, latent(occ: occ2 occ3 occ4 occ5 occ6 occ7 occ8 occ9 ///
>>                        occ10 occ11 occ12 occ13) post
>> // which means we can use -predict- to create the index
>> predict occ_status, xb equation(#2)
>> // and later use it in a regression as the dependent variable
>> reg occ_status grade i.race
>> *----------------------- end example ------------------------------
>> (For more on examples I sent to the Statalist see:
>> )
>> You might also consider going for a complete SEM model.
>> >there might be also a direction problem such as some variables might increase the index while they are decreasing but others might increase the index while they are increasing ?
>> That is not a problem, these two types of variables will automatically
>> get opposite signs on their weights.

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index