Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: AW: Different p-values


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: AW: Different p-values
Date   Thu, 5 Nov 2009 11:37:19 +0100

<> 

Omitting the -wald- option to -svy:tabulate-, the results do coincide:


*************
webuse nhanes2b, clear
svy: tabulate race diabetes/*, wald */ 

tabout race diabetes using table1.xls, c(col) f(4 0)  /* 
*/ replace clab(percent Count) svy nlab(samplesize) /* 
*/ stats(chi2) per
*************

Easy answer: -tabout- has no -passthru- for the -wald- option, so it is only
natural for the results to be different...


HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Rajaram
Subramanian Potty
Gesendet: Donnerstag, 5. November 2009 11:22
An: statalist@hsphsun2.harvard.edu
Betreff: st: Different p-values

Dear all,
I am getting different p-values as well as uncorrected chi-square
value when I run tabout and the SVY:tab why. following is the results

. tabout typo icvi ///
> using "D:\My Documents\table1.xls",  c(col) f(4 0)   replace clab(percent
Count)svy nla
> b(samplesize) stats(chi2) per
Survey results being calculated
----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5
.......
Table output written to: D:\My Documents\table1.xls

        icvi
Type of PSU     1       2       Total   samplesize
        percent percent percent
Home    52.6991 55.7778 54.2406 209
Brothel 20.8022 22.3111 21.5576 109
Public place    26.4987 21.9111 24.2018 97
Total   100.0000        100.0000        100.0000        415

Pearson: Uncorrected chi2(2) = 1.1931
Design-based F(1.45, 74.01) = 7.1319 Pr = 0.004

.
end of do-file

. svy:tab icvi typo, wald
(running tabulate on estimation sample)

Number of strata   =         1                  Number of obs      =
415
Number of PSUs     =        52                  Population size    =
415.441
                                                Design df          =
51

--------------------------------------------------
          |              Type of PSU
     icvi |     Home   Brothel  Public p     Total
----------+---------------------------------------
        1 |    .2631     .1039     .1323     .4993
        2 |    .2793     .1117     .1097     .5007
          |
    Total |    .5424     .2156      .242         1
--------------------------------------------------
  Key:  cell proportions

  Wald (Pearson):
    Unadjusted    chi2(2)         =   13.6306
    Adjusted      F(2, 50)        =    6.6817     P = 0.0027


Thanks and regards,

RAJA
*
*   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/


*
*   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/



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