st: Problems with standard errors using xi3, svy and ologit

[Iain Lang <iain.lang@pms.ac.uk>]

Dear Statalist members

I'm running models in Stata 9 using xi3, svy and ologit. This combination seems to produce very large standard errors, and these don't occur when I use xi instead of xi3. An example is pasted below (using a binary outcome as an example). Has anyone else encountered similar problems? Any help or comments appreciated!

With regards
Iain



. xi3: svy: ologit lbdbr2lc riagendr ridageyr ridreth1 bmicat dmdeduc , or
(running ologit on estimation sample)

Survey: Ordered logistic regression

Number of strata   =         1                  Number of obs      =      1952
Number of PSUs     =      1952                  Population size    =  69072325
                                                Design df          =      1951
                                                F(   5,   1947)    =      0.01
                                                Prob > F           =    1.0000

------------------------------------------------------------------------------
             |             Linearized
             | Odds Ratio   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
lbdbr2lc     |
    riagendr |   .9629752    3.59095    -0.01   0.992     .0006419     1444.54
    ridageyr |   1.008208   .0808595     0.10   0.919     .8614708    1.179941
    ridreth1 |    1.22529   2.015331     0.12   0.902     .0486779    30.84224
      bmicat |   .8493934   1.889173    -0.07   0.942     .0108328    66.60063
     dmdeduc |   .9069374   1.857839    -0.05   0.962     .0163241    50.38777
-------------+----------------------------------------------------------------
cut1         |
       _cons |   1.697923   9.050466     0.19   0.851    -16.05167    19.44752
------------------------------------------------------------------------------



. xi: svy: ologit lbdbr2lc riagendr ridageyr ridreth1 bmicat dmdeduc , or
(running ologit on estimation sample)

Survey: Ordered logistic regression

Number of strata   =         1                  Number of obs      =      1952
Number of PSUs     =      1952                  Population size    =  69072325
                                                Design df          =      1951
                                                F(   5,   1947)    =      3.52
                                                Prob > F           =    0.0036

------------------------------------------------------------------------------
             |             Linearized
    lbdbr2lc | Odds Ratio   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
    riagendr |   .9629752   .1444957    -0.25   0.802     .7174835    1.292464
    ridageyr |   1.008208   .0032874     2.51   0.012     1.001782    1.014676
    ridreth1 |    1.22529   .0825729     3.01   0.003     1.073595     1.39842
      bmicat |   .8493934   .0757742    -1.83   0.067     .7130602    1.011793
     dmdeduc |   .9069374   .0754373    -1.17   0.240      .770428    1.067634
-------------+----------------------------------------------------------------
       /cut1 |   1.697923   .3616552     4.69   0.000      .988652    2.407195
------------------------------------------------------------------------------

*
*   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/