Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

st: MCA postestimation commands


From   "Kirsten Stoebenau" <kstoeben@uottawa.ca>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: MCA postestimation commands
Date   Wed, 14 Apr 2010 14:34:41 -0400

Dear statalistserve users,

I am trying to use multiple correspondence analysis (MCA) as an
alternate method by which to construct a wealth index using Stata 10.


I have successfully run the MCA (I think).


mca pphold2 mur plancher plafond toit ownrent cook light toilet nopotty
Q123A Q123B1 Q123C-Q123E owater beds tables chairs salon radio TV ordi
phone fridge bike moto car sarety field omby poulet poultry

Now I need to sum the scores generated for each coordinate for the first
dimension of the MCA. 

In other words, I need to sum the weights generated from the MCA for
each coordinate (many of these vars are not binary but categorical with
4-6 possible responses, therefore there are over 100 coordinates
involved).  

I do not know how to do this.  I suspect it involves some combination of
commands including predict, scores (or rowscores).  

I would really appreciate some input on MCA postestimation commands, and
would welcome an example .do file.


Thank you,
Kirsten Stoebenau

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Richard
Ochmann
Sent: Wednesday April 14, 2010 2:16 PM
To: statalist@hsphsun2.harvard.edu
Subject: Antwort: st: Three way table with tabout

this might be of interest to you:
http://www.stata.com/statalist/archive/2009-03/msg01154.html

best,
rich

owner-statalist@hsphsun2.harvard.edu schrieb am 14.04.2010 19:29:51:

> Dear Statalisters,
> 
> Using Stata 9.2.
> 
> Is it possible to get a three way table from tabout?
> 
> I would like to have a table of health status by age groups for men
> and bellow another one for women that I can easily export to Excel,
> but I'd rather have in the first row the health status variable label,
> in the second the first value label for sex (men), in the subsequent
> rows the percentages of different health status by age groups in men,
> then the second value label for sex (women) and finally the
> percentages of health status by age groups in women.
> 
> I've tried with topf:
> 
> tabout agegroups healthstatus using luisa.xls if sex==1, replace svy
> c(row ci) per f(1 1) layout(cb) h3(nil) cisep(-) ///
> 
> npos(col)style(tab)stats(chi2) topf(top.txt) topstr(MEN)
> 
> tabout agegroups healthstatus using luisa.xls if sex==2, append svy
> c(row ci) per f(1 1) layout(cb) h3(nil) cisep(-) ///
> 
> npos(col)style(tab)stats(chi2)topf(top.txt) topstr(WOMEN)
> 
> 
> 
> but then I get the sex value labels before the health status variable
> label, which is not the natural way to show the results.
> 
> Tabout does not support -bysort sex-
> 
> Many thanks,
> 
> Angel Rodriguez-Laso
> *
> *   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/

*
*   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   |   Site index