[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: setting e(sample)
> -----Original Message-----
> From: Stephen P. Jenkins [mailto:firstname.lastname@example.org]
> Sent: Thursday, March 27, 2003 10:19 AM
> To: email@example.com
> Subject: st: setting e(sample)
> Advice please about how to set the e(sample) function
> within an e class program.
> -ereturn b V post, esample(varname)- in version 8, and
> -est b V post, esample(varname)- in version 7,
> are the commands that the manuals refer to for setting e(sample).
> However both appear to assume that the program has created a
> coefficient vector ("b") and varcov matrix ("V").
> My problem is that my program does not create these (the
> estimates are
> built up in a non-regression based way).
> Is there anyway of creating e(sample) then?
A worst-case approach would be to create a "fake" b and V. This is the
strategy used by -svymean- and companion commands, when the -complete-
option is not specified.
After a call to -svymean- with the available option, for example, b and
V are as follows:
. mat list e(b)
. mat list e(V)
* For searches and help try: