[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: -gologit2- and testing the difference between coefficients
At 08:18 AM 3/29/2007, Herve STOLOWY wrote:
There are various ways to this; as others have
said, you can read more on my website. To do
specifically what you ask, you can do an LR test, e.g. do something like
I use the -gologit2- command (downloadable from ssc). Here is my syntax:
xi, prefix(): gologit2 format size1 auditor_d
standards_d for_list sales_int instit_for lev2 i.gics4, v1 nolabel
The dependent variable, format is coded 0, 1 or
2. I get two equations and, consequnetly, two panels of results.
I would like to know if is possible to test, for
a given variable, if the two coefficients in
each equation are different from one another? To
be clearer, I have the variable sales_int. In
panel 1, the coefficient is 1.314. In panel 2,
the coefficient for the same variable is 1.913.
Both are significant at the 0.10 level. Is there
a way to test that 1.314 is statistically different from 1.913?
gologit2 y x1 x2 x3, store(m1) lrf
gologit2 y x1 x2 x3, pl(x1) store(m2) lrf
lrtest m1 m2
In the first model you are allowing the effects
of x1 to differ across panels. In the 2nd model,
The -pl- (parallel lines) option will force the
effects of x1 to be the same across panels. You
can then do a LR chi-square contrast between the two models.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
* For searches and help try: