Re: st: standardised coefficients after lincom

["Roger B. Newson" <r.newson@imperial.ac.uk>]

What I would do is to use -lincomest- (downloadable from SSC), instead 
of -lincom-, so the linear combination and its variance are saved as 
estimation results. And then use -parmest- (downloadable from SSC) to 
create a 1-observation dataset with data on estimates, standard errors, 
confidence limits, t- or z-statistics, P-values and other parameter 
attributes. See Section 3.3 of Newson (2003) for en example of the use 
of -parmest- after -lincomest-.

Best wishes

Roger

Newson R. Confidence intervals and p-values for delivery to the end 
user. The Stata Journal 2003; 3(3): 245-269. Download from
http://www.stata-journal.com/article.html?article=st0043

Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
UNITED KINGDOM
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Email: r.newson@imperial.ac.uk
Web page: http://www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/

Opinions expressed are those of the author, not of the institution.

On 06/09/2013 22:05, Christopher Hein wrote:
> Dear fellow users,
>
> I would like to compute the  standardised coefficient after a linear combination test (lincom  command). In to complicate things all my variables I am using in lincom
>
> lincom Xvar1+Xvar2+Xvar3
>
> are interactions of a  continuous variable and a dummy. Now I know that some disciplines aren't  fond of standardised coefficients. This aside, I have found out that to  compute the standardised coefficient of an interaction variable (that I created manually, not by using xi:) STATA uses the  standard deviation of the corresponding un-interacted variable. To  compute the standardised coefficient STATA uses the standard error of  the estimate and NOT the standard deviation of the dummy variable.
>
> So my question now is first: how to compute the standardised coefficient of any linear combination.
> And secondly: what should I do in my case?
>
> Note the normal formula to compute the standardised coefficient for variable X is:
> beta=rawb_X*(sd_X/sd_Y),  where sd_X is the standard deviation of variable X and sd_Y the standard  deviation of the dependent variable.
>
> Best,
> Christopher F. Hein
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/