Re: st: sqreg -test- at each quantile

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 21/3/11, Samantha Batchelor wrote:
> I'm running a quantile regression including ethnicity with
> 5 levels as below.
> xi: sqreg vocab i.gender i.mothered i.children i.ethnicity
> standards, q(.2 .4 .6 .8) reps(500)
> 
> When I use:
> test _Iethnicity_2 _Iethnicity_3 _Iethnicity_4
> _Iethnicity_5
> to test the effect of ethnicity, Stata tests it across all
> the quantiles whereas I want it separately for each
> quantile.

That is correct. If you do not specify which equation (in case
of -sqreg- which quantile) a variable name belongs to, then 
-test- will assume that it has to take all of them. You can 
tell -test- which equation to look at by preceding the 
parameters with -[eqname]:- where eqname is the name of the 
equation. I find it often easier to refer to numbers, i.e. 
the first, second, etc. equation with #1, #2, etc.:

*---------------- begin example -----------
sysuse auto, clear
sqreg price weight length foreign, ///
      quantile(.25 .5 .75) reps(100)

// using names
test [q25]: weight length
test [q50]: weight length
test [q75]: weight length

// with equation numbers you can
// easily use loops:
forvalues i = 1/3 {
	test [#`i']: weight length
}
*---------------- end example -------------
(For more on examples I sent to the Statalist see: 
http://www.maartenbuis.nl/example_faq )

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/