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, statalist.org is already up and running.


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

st: Re: standardized coefficients from a probit model for path analysis using -listcoef-


From   Hilary Taylor <Hilary.Taylor@bristol.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: standardized coefficients from a probit model for path analysis using -listcoef-
Date   Tue, 18 Sep 2012 11:13:51 +0100

Thanks for your kind reply Martin. However my data has a binary dependent variable and ALL of the others (direct and indirect variables) are continuous, so this is not suitable for -ldecomp-. Please correct me if I'm wrong.

If I use the syntax:

-ldecomp binaryvar, direct(contvar1) indirect(contvar2) or-

I receive the 'matsize too small' error

I'd be very grateful for any further help you, or anyone else on the list could offer.

Many thanks

Hilary

--On 13 September 2012 16:30 +0100 Hilary Taylor <ht4439@bristol.ac.uk> wrote:

Hi, I would be very grateful if you would be able to help me with the
following question:

I am constructing a path analysis that has a binary outcome variable (all
the other variables are continuous).  For the models with continuous
outcome I am using multiple regression with the option -beta- to acquire
fully standardized coefficients.  For the model with the binary outcome I
am using -probit- and then following this up with -listcoef- (STB-57:
sg152)and am reading from the 'bStdXY' column - the fully standardized
coefficients.

Could you tell me if my result from 'bStdXY' is the best equivalent for
me to use in a model along with results from -beta-?

Many thanks



----------------------
Hilary Taylor
Research Assistant
Academic Rheumatology
Musculoskeletal Research Unit
School of Clinical Sciences
University of Bristol
Avon Orthopaedic Centre
Southmead Hospital
Westbury-on-Trym,
Bristol. BS10 5NB

Tel: 0117 323 6187
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index