st: Pmatch2 and random

["Gauri Khanna" <gwkhanna@hotmail.com>]

Dear Stata list,

I am running the psmtach2 command to estimate propensity scores. I use Stata 
9.2 and psmatch2 is updated.

While running this command, in my output I get a comment:

"There are observations with identical propensity score values.
The sort order of the data could affect your results.
Make sure that the sort order is random before calling psmatch2"

So I do the following
-gen random=uniform()
sort random-

but still get the same message, I also try with -set seed- as below but get 
the same message.

-set seed 12345
-gen random=uniform()
sort random-

I copy below my command and output. Does anyone know how to correct this 
problem?
.
. psmatch2 waterpipe sexhhead v152 v012 ageresp2 aware  ///

> v512 v715 eduhusb v730 partnerage2 v025 housetype2 ///
> sh42 ownerTV hv211 sh47q, out(h11) n(5) logit
Logistic regression                               Number of obs   =      
24869
                                                 LR chi2(16)     =    
6171.00
                                                 Prob > chi2     =     
0.0000
Log likelihood = -13440.218                       Pseudo R2       =     
0.1867

------------------------------------------------------------------------------
  waterpipe |      Coef.   Std. Err.      z    P>|z|     [95% Conf. 
Interval]
-------------+----------------------------------------------------------------
   sexhhead |    .081646   .0614635     1.33   0.184    -.0388202    
.2021123
       v152 |  -.0036941   .0010471    -3.53   0.000    -.0057463    
-.001642
       v012 |   .0361599   .0220871     1.64   0.102      -.00713    
.0794498
   ageresp2 |   .0001226   .0003905     0.31   0.754    -.0006428     
.000888
      aware |     .51381   .0374203    13.73   0.000     .4404675    
.5871525
       v512 |   -.066041    .005295   -12.47   0.000     -.076419    
-.055663
       v715 |   .0116712   .0090949     1.28   0.199    -.0061545     
.029497
    eduhusb |  -.0002637   .0006224    -0.42   0.672    -.0014835    
.0009562
       v730 |   .0377528   .0103074     3.66   0.000     .0175506     
.057955
partnerage2 |  -.0004689   .0001196    -3.92   0.000    -.0007032   
-.0002346
       v025 |  -1.486734   .0365479   -40.68   0.000    -1.558367   
-1.415102
 housetype2 |  -.0481205   .0312731    -1.54   0.124    -.1094148    
.0131737
       sh42 |  -.2851831   .0532543    -5.36   0.000    -.3895597   
-.1808065
    ownerTV |   .5799184   .0394479    14.70   0.000     .5026019     
.657235
      hv211 |   .2489998   .0539778     4.61   0.000     .1432052    
.3547944
      sh47q |  -.7165624   .0595988   -12.02   0.000    -.8333739   
-.5997508
      _cons |   .6628973   .3185432     2.08   0.037     .0385641     
1.28723
------------------------------------------------------------------------------
There are observations with identical propensity score values.
The sort order of the data could affect your results.
Make sure that the sort order is random before calling psmatch2.
----------------------------------------------------------------------------------------
       Variable     Sample |    Treated     Controls   Difference         
S.E.   T-stat
----------------------------+-----------------------------------------------------------
            h11  Unmatched | .414652169   .389711613   .024940556    
.01043801     2.39
                       ATT | .414652169   .365248601   .049403568   
.014874442     3.32
----------------------------+-----------------------------------------------------------
Note: S.E. for ATT does not take into account that the propensity score is 
estimated.

          | psmatch2:
psmatch2: |   Common
Treatment |  support
assignment | On suppor |     Total
-----------+-----------+----------
Untreated |    15,396 |    15,396
  Treated |     9,473 |     9,473
-----------+-----------+----------
    Total |    24,869 |    24,869

Sincerely,

Gauri

_________________________________________________________________
Don't just search. Find. Check out the new MSN Search! 
http://search.msn.com/

*
*   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/