Re: st: Re: Factor analysis and dummy variables.

[adiallo5@worldbank.org]

Hi Friedrich,

I couldn't respond to your email cause I was not
in my office last  days.

You're right.

By normal, I did not mean the "normal distribution"
but the distribution I usually obtain with factor command
(the "normal" distribution in my mind). It is just a typo.

The distributions of indexes produced by the polychoricpca
command are also skewed, and resemble to those I usually
obtained with the Filmer method. Less skewed, but skewed anyway.

I will however use this program in the future in place of the usual factor if
I have dummies variables. It is the best choice I can make so far.

Thanks for your support.

Amadou.



                                                                                                                                           
                      Friedrich Huebler                                                                                                    
                      <huebler@rocketmail.com>         To:       statalist@hsphsun2.harvard.edu                                            
                      Sent by:                         cc:                                                                                 
                      owner-statalist@hsphsun2.        Subject:  st: Re: Factor analysis and dummy variables.                              
                      harvard.edu                                                                                                          
                                                                                                                                           
                                                                                                                                           
                      12/13/2004 10:54 AM                                                                                                  
                      Please respond to                                                                                                    
                      statalist                                                                                                            
                                                                                                                                           
                                                                                                                                           
                                                                                                                                           
                                                                                                                                           




Amadou,

Do you expect the wealth score to be normally distributed? The
distribution of the wealth score depends on the distribution of
household assets in your data.

Friedrich Huebler

--- adiallo5@worldbank.org wrote:
> I've tried the polychoric procedure this week-end.
> Not only it is too long to produce final results (it takes
> a whole day for each data set) but it is also skewed.
> Not as much as the traditional Filmer-Pritchett method,
> but skewed nonetheless. My distribution obtained is far
> from the normal.




__________________________________
Do you Yahoo!?
Take Yahoo! Mail with you! Get it on your mobile phone.
http://mobile.yahoo.com/maildemo
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/




*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/