Hi Clive
Thanks for your input. I still have a question. Does
the command collin incorporate strata, psu and
pweight?
I ran the svyreg and collin as you suggested. But
when I ran svyreg for each of the independent
variables to calculate the VIF manually, the VIF
values are slightly different than the output from
collin.
So it looks like collin does not take into account
strata, psu, and pweights. Am I right?
Thanks for your time.
Anju
--- Clive Nicholas <[email protected]>
wrote:
> Anju Parthan wrote:
>
> > I have complex survey data. I am trying to run vif
> > after svyregress, but I get this error message
> >
> > . vif
> > last estimates not found
> > r(301);
> >
> > How can I calculate vif with svyregress?
>
> Easy. Download Phil Ender's -collin- package from
> SSC. An example, taken
> from one of my own 'cloned' datasets:
>
> . use ees99, clear
>
> . svyset [pweight=weight]
> pweight is weight
>
> . svyreg probvcon sex age educ turecode
>
> Survey linear regression
>
> pweight: weight
> Number of obs = 920
> Strata: <one>
> Number of strata = 1
> PSU: <observations>
> Number of PSUs = 920
>
> Population size = 924.698
> F(
> 4, 916) = 5.76
> Prob
> > F = 0.0001
>
> R-squared = 0.0346
>
----------------------------------------------------------------------------
> probvcon | Coef. Std. Err. t P>|t|
> [95% Conf. Interval]
>
-----------+----------------------------------------------------------------
> sex | .0952869 .2302624 0.41 0.679
> -.3566143 .5471881
> age | -.0283479 .0078918 -3.59 0.000
> -.0438359 -.0128599
> educ | .0153538 .0173196 0.89 0.376
> -.0186367 .0493443
> turecode | -.4211906 .1369806 -3.07 0.002
> -.6900217 -.1523596
> _cons | 59.86004 15.52017 3.86 0.000
> 29.40094 90.31913
>
----------------------------------------------------------------------------
>
> . collin probvcon sex age educ turecode
>
> Collinearity Diagnostics
> SQRT
> Cond Cond R-
> Variable VIF VIF Tolerance Eigenval
> Index1 Index2 Squared
>
----------------------------------------------------------------------------
> probvcon 1.03 1.01 0.9749 1.1722 1
> 1.0000 1.0000 0.0251
> sex 1.01 1.01 0.9885 1.1475 2
> 1.0107 2.4812 0.0115
> age 1.03 1.01 0.9741 0.9868 3
> 1.0899 3.2101 0.0259
> educ 1.02 1.01 0.9791 0.8671 4
> 1.1627 4.1625 0.0209
> turecode 1.02 1.01 0.9843 0.8264 5
> 1.191 8.3130 0.0157
> 6
> 391.5044
>
----------------------------------------------------------------------------
> Mean VIF 1.02 Condition
> Number 1.1910 391.5044
> Determinant of correlation
> matrix 0.9511
> Cond Index1 from deviation
> SSCP (no intercept)
> Cond Index2 from scaled raw
> SSCP (w/ intercept)
>
> CLIVE NICHOLAS |t: 0(044)7903 397793
> Politics |e: [email protected]
> Newcastle University |http://www.ncl.ac.uk/geps
>
> *
> * For searches and help try:
> *
> http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
=====
____________________________________________________________
Anju Parthan,
Doctoral Candidate,
The University of Texas at Austin, PHAR-PHARMACY ADMIN
1 UNIVERSITY STATION A 1930, AUSTIN, TX-78712
Tel: (512) 459-4942; Fax: (512) 471-8762
__________________________________
Do you Yahoo!?
Yahoo! Mail - 250MB free storage. Do more. Manage less.
http://info.mail.yahoo.com/mail_250
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
