Re: st: parmby: how to get value lables in output?

[Roger Newson <r.newson@imperial.ac.uk>]

The best answer to this is probably to use the -nolabel- option for the 
-proportion- command, to extract the numeric values from the -parm- 
variable in the -parmby- output dataset, and to reconstruct the variable 
-DE4a_5yr- in the output dataset using the official Stata commands 
-split- and -destring- with the -descsave- package, which ypu can 
download from SSC. The -descsave- command is an extended version of 
-describe-, and is a Stata program which writes Stata programs.

Your code might be:

tempfile df0
descsave DE4A_5yr, do)`"`df0'"')
parmby "svy: proportion DE4A_5yr, nolabel missing", norestore 
rename(estimate Proportion)
split parm, parse(:) gene(S_)
destring S_2, gene(DE4a_5yr)
drop S_*
do `"`df0'"'
list

The -tempfile- command creates a name for a temporary do-file. The 
-descsave- command creates that temporary do-file, which contains 
commands to reconstruct any variable labels, value labels, formats and 
storage types for the variable -DE4A_5yr-. The -parmby- command is like 
the one in Anupam's code, but it does not rename the variable -parm- in 
the output dataset, and -proportion- has the -nolabel- option, so that 
the new variable -parm- will contain only numeric values for -DE4A_5yr-. 
The -split- command inputs the -aprm- command and outputs 2 new 
variables -S_1- and -S_2-, containing the contents of -parm- to the left 
and to the right of the colon (:). The -destring- command inputs S_2, 
which will contain character representations of the numeric values of 
-DE4A_5yr-, and outputs the numeric variable -DE4A_5yr-. The -drop- 
command drops the temporary variables -S_1- and -S_2-. The -do- command 
executes the temporary do-file to reconstruct the variable attributes 
(including value labels) for the variable -DE4A_5yr-. Finally, the 
-list- command displays the output dataset, which should now include the 
new variable -DE4A_5yr-, reconstructed in the output dataset, complete 
with value labels.

I hope this helps.

Best wishes

Roger


Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
UNITED KINGDOM
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Email: r.newson@imperial.ac.uk
Web page: http://www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/

Opinions expressed are those of the author, not of the institution.

On 01/05/2010 09:05, Anupam wrote:
> How to get value labels in the output from parmby? Instead of _prop_1
> prop_2, etc., I want value labels (see below). Thanks for your
> consideration.
>
> Command and output are below:
>
> . parmby "svy: proportion DE4A_5yr, missing", norestore rename(parm de4a_5yr
> estimate Proportion)
>
> Command: svy: proportion DE4A_5yr, missing
>
> (running proportion on estimation sample)
>
>
>
> Survey: Proportion estimation
>
>
>
> Number of strata =       1          Number of obs    =  215754
>
> Number of PSUs   =    2474          Population size  = 1.0e+09
>
>                                      Design df        =    2473
>
>
>
>        _prop_1: DE4A_5yr = 0-
>
>        _prop_2: DE4A_5yr = 5-
>
>        _prop_3: DE4A_5yr = 10-
>
>        _prop_4: DE4A_5yr = 15-
>
>        _prop_5: DE4A_5yr = 20-
>
>        _prop_6: DE4A_5yr = 25-
>
>        _prop_7: DE4A_5yr = 30-
>
>        _prop_8: DE4A_5yr = 35-
>
>        _prop_9: DE4A_5yr = 40-
>
>       _prop_10: DE4A_5yr = 45-
>
>       _prop_11: DE4A_5yr = 50-
>
>       _prop_12: DE4A_5yr = 55-
>
>       _prop_13: DE4A_5yr = 60-
>
>       _prop_14: DE4A_5yr = 65-
>
>       _prop_15: DE4A_5yr = 70-
>
>       _prop_16: DE4A_5yr = 75-
>
>       _prop_17: DE4A_5yr = 80-
>
>       _prop_18: DE4A_5yr = .
>
>
>
> --------------------------------------------------------------
>
>               |             Linearized         Binomial Wald
>
>               | Proportion   Std. Err.     [95% Conf. Interval]
>
> -------------+------------------------------------------------
>
> DE4A_5yr     |
>
>       _prop_1 |   .0066759   .0009649      .0047838     .008568
>
>       _prop_2 |    .001211   .0002921      .0006382    .0017839
>
>       _prop_3 |   .0009341   .0003057      .0003347    .0015335
>
>       _prop_4 |    .001101   .0003248      .0004642    .0017379
>
>       _prop_5 |   .0010596   .0002144      .0006392      .00148
>
>       _prop_6 |   .0018453   .0006205      .0006286    .0030621
>
>       _prop_7 |   .0010639    .000279      .0005167    .0016111
>
>       _prop_8 |   .0015552   .0004017      .0007674    .0023429
>
>       _prop_9 |   .0012013   .0002554      .0007004    .0017022
>
>      _prop_10 |   .0021859   .0004139      .0013742    .0029975
>
>      _prop_11 |   .0014081   .0002065      .0010031    .0018131
>
>      _prop_12 |   .0020961   .0004735      .0011677    .0030246
>
>      _prop_13 |   .0032379   .0006099      .0020419    .0044339
>
>      _prop_14 |   .0061096   .0019506      .0022846    .0099346
>
>      _prop_15 |   .0054201    .000871      .0037121    .0071282
>
>      _prop_16 |   .0030363   .0004292      .0021947    .0038779
>
>      _prop_17 |   .0068777   .0006943      .0055161    .0082392
>
>      _prop_18 |   .9529809   .0028802       .947333    .9586288
>
> --------------------------------------------------------------
>
>
>
> *
> *   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/