Sorry Fatma
After a second thought i think I misread your email. The code i sent
you doesn't work with parameters, but with means for one variable by
gropus (which could be quintiles of a variable). I'm a little bit
confused as to what is the estimation that you performed before?
best
robert
On Fri, 15 Oct 2004 00:31:12 -0400, Robert Duval <[email protected]> wrote:
> One option is to do one-way analysis of variance... see comand
> oneway... your code might look like
>
> on y_var quantile_var, tabulate
>
> cheers,
> robert
>
>
>
> On Thu, 14 Oct 2004 17:41:42 +0300, fatma bircan <[email protected]> wrote:
> > Fatma Bircan
> > Middle East Technical University
> > Department of Economics
> > 210-2032
> >
> > ------ Forwarded message -------
> >
> > From: fatma bircan <[email protected]>
> > Reply-to: [email protected]:
> > [email protected]
> > Date: Thu, 14 Oct 2004 17:18:40 +0300
> >
> > Fatma Bircan
> > Middle East Technical University
> > Department of Economics
> > 210-2032
> >
> > How do I tset the equality of parameters across quantiles .
> >
> > I tried the following
> >
> > test [q10=q25=q50=q75=q90]: yrschl
> >
> > ( 1) [q10]yrschl - [q25]yrschl = 0
> > ( 2) [q10]yrschl - [q50]yrschl = 0
> > ( 3) [q10]yrschl - [q75]yrschl = 0
> > ( 4) [q10]yrschl - [q90]yrschl = 0
> >
> > F( 4, 5806) = 5.09
> > Prob > F = 0.0004
> >
> > But it doesnt give all the combinations. I f I specify all the
> > combinations then the df changes. What should I do?
> >
> > *
> > * 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/
> >
>
*
* 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/
