st: RE: differences in percentages across categories

[Nick Cox <n.j.cox@durham.ac.uk>]

And

Comparing Two Proportions from the Same Survey
C. J. Wild and G. A. F. Seber 
The American Statistician , Vol. 47, No. 3 (Aug., 1993), pp. 178-181

Nick 
n.j.cox@durham.ac.uk 


-----Original Message-----
From: Nick Cox 
Sent: 20 January 2012 13:25
To: 'statalist@hsphsun2.harvard.edu'
Subject: RE: differences in percentages across categories

This sounds like 

Difference of Proportions from the Same Survey
Alastair J. Scott and George A. F. Seber 
The American Statistician , Vol. 37, No. 4, Part 1 (Nov., 1983), pp. 319-320

I am not aware of a canned implementation in Stata. 

Nick 
n.j.cox@durham.ac.uk 


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Mirko Moro
Sent: 20 January 2012 10:47
To: statalist@hsphsun2.harvard.edu
Subject: st: differences in percentages across categories

Dear Statlisters,

Imagine I have 2 categorical variables, say Repair Record in 1978 and
Headroom (suppose I treat Headroom as categorical variable):

. sysuse auto
(1978 Automobile Data)

. tab rep78 headroom, row nofreq

    Repair |
    Record |                          Headroom (in.)
      1978 |       1.5        2.0        2.5        3.0        3.5
   4.0 |     Total
-----------+------------------------------------------------------------------+----------
         1 |     50.00      50.00       0.00       0.00       0.00
  0.00 |    100.00
         2 |      0.00      37.50       0.00       0.00      12.50
 25.00 |    100.00
         3 |      0.00      16.67      16.67      13.33      33.33
 10.00 |    100.00
         4 |     11.11       5.56      27.78      16.67      11.11
 27.78 |    100.00
         5 |      0.00      27.27      36.36      36.36       0.00
  0.00 |    100.00
-----------+------------------------------------------------------------------+----------
     Total |      4.35      18.84      20.29      15.94      18.84
 14.49 |    100.00


    Repair |
    Record |    Headroom (in.)
      1978 |       4.5        5.0 |     Total
-----------+----------------------+----------
         1 |      0.00       0.00 |    100.00
         2 |     12.50      12.50 |    100.00
         3 |     10.00       0.00 |    100.00
         4 |      0.00       0.00 |    100.00
         5 |      0.00       0.00 |    100.00
-----------+----------------------+----------
     Total |      5.80       1.45 |    100.00


I would like to test whether the percentage of car with headroom equal
to 1.5 inch vary across repair records, after that I wish to know
whether the percentage of car with headroom equal to 2.5 inch vary
across repair records, and so on.

Is there a way to do this or I need multinomial models with varying
baseline and reference categories?


*
*   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/