[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Mills ratio after bivariate probit

From   Sami Haile <>
Subject   Re: st: Mills ratio after bivariate probit
Date   Mon, 17 Nov 2008 10:09:21 -0800 (PST)

Thanks for the suggestions. To make my problem clrear, here
> is the way my model look
> Y1=sellers     Y2=buyers
> biprobit y1 y2 x1 x2 x3 x4 (pw=weight)
> Here I want to eastimate two selection parameters for both
> regimes, so that I can use them in the second step which is
> weighted two stage least square. I want to use this
> selection parameters as an instrumental variables in my
> second model, which looks like;
> ivreg  y1  x1 x2 (invmills1 = x4 x5) [pweight = weight)
> ivreg  y2 x1 x2  (invmills2=x4 x5) [pweight = weight)
> Invers mills here is the selection parameter from the
> biprobit, which considers the factors that affect the
> decision to sell and/or buy - in this case x3 x4 . This is
> what I thought if i am right, So I hope I made the problem
> clear now.
> thanks for your time and suggestion again.
> sami


*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index