Statalist


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

Re: st: Need help for chi-square test with survey command


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Need help for chi-square test with survey command
Date   Thu, 1 Oct 2009 09:07:00 -0500

Stata uses Rao-Scott corrections for the scale and degrees of freedom
of the independence test chi^2. It might have happened that something
went negative because of this corrections. For instance, in your
extended case, you lost 1.02 degrees of freedom to the design (compare
chi2(9) and F(7.98, something) ).

On Thu, Oct 1, 2009 at 8:19 AM, Mihir <mihir.statistics@gmail.com> wrote:
> Dear all:
>
> Anybody has any idea what can be done in the case below?
>
> Thanking you,
> Mihir
>
> On Wed, Sep 30, 2009 at 1:29 AM, Mihir <mihir.statistics@gmail.com> wrote:
>>
>> Dear all:
>>
>> I am stuck with a problem in pearson chi-square test with survey
>> command. I have setup survey setting for Nationwide Inpatient Survey
>> (NIS) data. I used hospital id as sampling unit, discwt as sampling
>> weight and stratum variable as strata as suggested on NIS website.
>> When I am trying to run chi-square test for independence between age
>> category and year of data collection from 1998 to 2007, it gives
>> proper result, but when I run the same command by retaining only two
>> years (1998 and 2007), it does not produce p-value. I don't understand
>> why it is happening? Can anybody help me - what I should do? I am also
>> getting similar results with other variables that same command works
>> with more year but doesn't work with two years.
>>
>> I have pasted my output for your ready reference.
>>
>> Thanking you in advance,
>> Mihir
>>
>> svyset hospid [pweight=discwt], strata(stratum) vce(linearized)
>>
>>      pweight: discwt
>>          VCE: linearized
>>     Strata 1: stratum
>>         SU 1: hospid
>>        FPC 1: <zero>
>>
>> svy: tabulate year age2cat, count column row obs percent format(%10.0g) pearson
>> (running tabulate on estimation sample)
>>
>> Number of strata   =        60                  Number of obs      =    157222
>> Number of PSUs     =      3270                  Population size    = 759816.12
>>                                                Design df          =      3210
>>
>> -------------------------------------------
>>          |             age2cat
>>     YEAR |  <65 year   >=65 yea      Total
>> ----------+--------------------------------
>>     1998 | 27548.394  10497.654  38046.048
>>          | 72.408029  27.591971        100
>>          | 4.9658285  5.1193873  5.0072705
>>          |      5452       2102       7554
>>          |
>>     1999 | 25591.467  9586.1825  35177.649
>>          | 72.749224  27.250776        100
>>          |  4.613076  4.6748901  4.6297582
>>          |      5265       1991       7256
>>          |
>>     2000 |  25067.72  9839.9109  34907.631
>>          | 71.811576  28.188424        100
>>          | 4.5186663  4.7986258  4.5942209
>>          |      5163       2032       7195
>>          |
>>     2001 | 24673.646  9882.7968  34556.443
>>          | 71.401001  28.598999        100
>>          | 4.4476311  4.8195399  4.5480007
>>          |      4983       1976       6959
>>          |
>>     2002 | 83751.067  30869.413  114620.48
>>          | 73.068152  26.931848        100
>>          | 15.096831  15.054075  15.085292
>>          |     17682       6513      24195
>>          |
>>     2003 | 80686.437  27375.013  108061.45
>>          |  74.66718   25.33282        100
>>          | 14.544405  13.349963  14.222053
>>          |     17002       5737      22739
>>          |
>>     2004 | 77406.999  26898.738  104305.74
>>          | 74.211641  25.788359        100
>>          | 13.953259  13.117698   13.72776
>>          |     16052       5540      21592
>>          |
>>     2005 | 74552.231  27032.143  101584.37
>>          | 73.389467  26.610533        100
>>          | 13.438663  13.182755    13.3696
>>          |     15263       5507      20770
>>          |
>>     2006 | 68720.522  26875.807  95596.329
>>          | 71.886152  28.113848        100
>>          | 12.387449  13.106515  12.581508
>>          |     14234       5538      19772
>>          |
>>     2007 | 66760.785  26199.193  92959.979
>>          | 71.816696  28.183304        100
>>          |  12.03419  12.776551  12.234536
>>          |     13813       5377      19190
>>          |
>>    Total | 554759.27  205056.85  759816.12
>>          | 73.012306  26.987694        100
>>          |       100        100        100
>>          |    114909      42313     157222
>> -------------------------------------------
>>  Key:  weighted counts
>>        row percentages
>>        column percentages
>>        number of observations
>>
>>  Pearson:
>>    Uncorrected   chi2(9)         =   91.4953
>>    Design-based  F(7.98, 25611.84)=    3.0966    P = 0.0017
>>
>> keep if year==1998|year==2007
>>
>> svy: tabulate year age2cat, count column row obs percent format(%10.0g) pearson
>> (running tabulate on estimation sample)
>>
>> Number of strata   =        60                  Number of obs      =     26744
>> Number of PSUs     =      1205                  Population size    = 131006.03
>>                                                 Design df          =      1145
>>
>> -------------------------------------------
>>           |             age2cat
>>      YEAR |  <65 year   >=65 yea      Total
>> ----------+--------------------------------
>>      1998 | 27548.394  10497.654  38046.048
>>           | 72.408029  27.591971        100
>>           | 29.210724   28.60642  29.041449
>>           |      5452       2102       7554
>>           |
>>      2007 | 66760.785  26199.193  92959.979
>>           | 71.816696  28.183304        100
>>           | 70.789276   71.39358  70.958551
>>           |     13813       5377      19190
>>           |
>>     Total | 94309.179  36696.848  131006.03
>>           | 71.988428  28.011572        100
>>           |       100        100        100
>>           |     19265       7479      26744
>> -------------------------------------------
>>   Key:  weighted counts
>>         row percentages
>>         column percentages
>>         number of observations
>>
>>
>>   Pearson:
>>     Uncorrected   chi2(1)         =    0.9557
>>     Design-based  F(., .)         =         .     P =      .
>>
>> *
>> *   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/
>



-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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