Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: RE: Command format svytest


From   "Siyam,AA (pgr)" <A.A.Siyam@lse.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: RE: Command format svytest
Date   Fri, 13 Sep 2002 17:02:18 +0100

Thanks to Bryan Sayer for his reply.

We are not sure of the format since the example we can see in the Stata manuals (version 6.0) is using dummy variables to indicate the explanatory variables.  Our output is as follows

. xi:svyologit hivchance i.gender i.v130
i.gender          _Igender_1-2        (naturally coded; _Igender_1 omitted)
i.v130            _Iv130_1-6          (naturally coded; _Iv130_1 omitted)
Survey ordered logistic regression
pweight:  v005                                    Number of obs    =      7479
Strata:   v022                                    Number of strata =        84
PSU:      v001                                    Number of PSUs   =       176
                                                  Population size  = 7.406e+09
                                                  F(   5,     88)  =     12.74
                                                  Prob > F         =    0.0000

------------------------------------------------------------------------------
   hivchance |      Coef.    Std. Err.      t    P>|t|    [95% Conf. Interval]
-------------+----------------------------------------------------------------
  _Igender_2 |   .3297621     .047393     6.96   0.000    .2356355    .4238887
    _Iv130_2 |  -.1641766    .0693238    -2.37   0.020   -.3018596   -.0264936
    _Iv130_3 |  -.2606368    .0670014    -3.89   0.000   -.3937074   -.1275663
    _Iv130_4 |  -.1112323    .1399389    -0.79   0.429    -.389163    .1666985
    _Iv130_6 |   .0841716    .4875742     0.17   0.863   -.8841928    1.052536
-------------+----------------------------------------------------------------
       /cut1 |  -.4138414     .042807    -9.67   0.000   -.4988597    -.328823
       /cut2 |    .387743    .0460213     8.43   0.000    .2963407    .4791454
       /cut3 |    1.04474    .0515826    20.25   0.000    .9422925    1.147187
       /cut4 |   1.678771    .0655638    25.61   0.000    1.548556    1.808986
------------------------------------------------------------------------------

We wish to use svytest to test the significance of the explanatory variable "v130" - we are not sure how to specify that.

Many thanks for your help in advance,

Amani


-----Original Message-----
From: Sayer, Bryan [mailto:BSayer@s-3.com]
Sent: 13 September 2002 14:33
To: 'statalist@hsphsun2.harvard.edu'
Subject: st: RE: Command format svytest


The test for each coefficient is just the t-test in the output.  Use -svylc-
and -svytest- to test linear combinations of coefficients.

Bryan Sayer
Statistician, SSS Inc.
bsayer@s-3.com

-----Original Message-----
From: Siyam,AA (pgr) [mailto:A.A.Siyam@lse.ac.uk]
Sent: Friday, September 13, 2002 6:33 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: Command format svytest


Dear colleagues, 

I am sorry for what maybe a trivial question.  Would anyone know the format
for running an "svytest" post a "svyologit" command as such

xi: svyologit hivchance i.gender i.region i.educg i.marstatus

We wish to perform individual hypotheses testing of each explanatory
variable to asses the goodness-of-fit (since svyologit is estimated using
pseudo-likelihood).


Many thanks for your help in advance.

Amani
*
*   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/
*
*   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/
*
*   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/



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