Hi, thanks for your help,
I have run the sheafcoef command - can I just check that the values I need are p1, p2 etc and these can be interpreted in the same way as a standardised beta coefficient?
. sheafcoef, latent( _Ihighested_2 _Ihighested_3 _Ihighested_4 ; _IMothers_B_2 _IMothers_B_3 )
------------------------------------------------------------------------------
Group27_we~t | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
p1 | 16.14495 2.721279 5.93 0.000 10.80729 21.48261
a1__Ihighe~2 | 1.534664 .6632412 2.31 0.021 .2337487 2.83558
a1__Ihighe~3 | 1.459557 .7091874 2.06 0.040 .0685204 2.850594
a1__Ihighe~4 | 3.857852 .4413342 8.74 0.000 2.992196 4.723507
p2 | 6.232302 2.726072 2.29 0.022 .8852447 11.57936
a2__IMothe~2 | -1.579171 .7521499 -2.10 0.036 -3.054477 -.1038659
a2__IMothe~3 | -2.571578 .5937274 -4.33 0.000 -3.736145 -1.407011
_cons | 149.9236 11.31615 13.25 0.000 127.7275 172.1197
------------------------------------------------------------------------------
----------------------------------------
> Date: Thu, 3 Sep 2009 13:52:38 +0000
> From: [email protected]
> Subject: Re: st: regression using dummy variables
> To: [email protected]
>
> --- On Thu, 3/9/09, Amy Jennings wrote:
>> I am new to STATA and am currently doing (trying) multiple
>> regression using dummy coded categorical variables, I want
>> to compare my coefficients so I can assess the relative
>> strength of each predictor as I would in multiple regression
>> with continuous predictors. is it possible to get an
>> overall coefficient for my dummy coded variables?
>
> Yes, this is what so called sheaf coefficients where designed
> to do, see: Heise, David R. (1972). Employing nominal
> variables, induced variables, and block variables in path
> analysis. Sociological Methods & Research, 1(2): 147--173.
>
> These sheaf coefficients can be computed in Stata using the
> -sheafcoef- package, which you can install by typing in
> Stata: -ssc install sheafcoef-
>
> Hope this helps,
> Maarten
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
> http://www.maartenbuis.nl
> --------------------------
>
>
>
>
> *
> * 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/
_________________________________________________________________
Use Hotmail to send and receive mail from your different email accounts.
http://clk.atdmt.com/UKM/go/167688463/direct/01/
*
* 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/
