[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: beta response modelling [was: RE: RE: crudity]
-betafit- allows each of two parameters to depend on covariates,
. ssc type betafit.hlp
will indicate. Its parameterisation of the beta distribution
is what I sense is conventional in the literature.
Credit where credit is due: although the presentation of
-betafit- is my responsibility, most of the code is a
straight borrowing from something else by Stephen Jenkins.
> Without having seen the code for -betafit- I can make a very
> educated guess
> that mine is the most crude. Does -betafit- allow expreesion of both
> parameters (or better, their log transforms) by linear combinations of
* For searches and help try: