[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: ivprob and collinearity
I think this has been discussed previously on Statalist.
I can't recall the outcome but you could try searching
> I have a query on the ivprob command.
> After having set trace on I discovered where I got the
> conformability error
> message - it is after the last line of this bit of program
> /* get lee model estimates */
> cap estimates drop lastpbt
> probit `depvar' `fitted' `exog' if `touse'
> matrix tmp = get(_b)
> matrix beta=tmp[1,1..`nendog']
> matrix means=get(mns)
> matrix colnames means = `endog' `exog' _cons
> The probit part of the command automatically excludes
> collinear variables and
> therefore the 'exog' list and the list of regressors are
> different so that
> when stata tries to assign column names - there are less
> columns than names in
> the varlist.
> Presumably this problem will reoccur at later stages of the program.
> Can anyone suggest a simple way of amending this program to
> deal with this
> problem? My programming skills are not so great.
* For searches and help try: