[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: STATA: multivariate probit w/ bootstrap

From   "Daniel R. Petrolia" <>
To   <>
Subject   Re: st: STATA: multivariate probit w/ bootstrap
Date   Fri, 02 May 2008 08:18:27 -0500

Arne and Stas,
  Thanks much for your very generous help with my problem.  I think we now have at least two more options to derive some estimates thanks to your suggestions.  

Dan Petrolia

>>> "Arne Risa Hole" <> 5/2/2008 5:28 AM >>>
I agree with Stas that -nlcom- is likely to be a good alternative to
the bootstrap but it's worth keeping in mind that it will not be very
accurate if the distribution of mean WTP is highly non-normal. This
could be the case since WTP is often derived as a function of the
ratio of coefficient estimates. In this case the parametric bootstrap
represents a compromise between accuracy (-bootstrap-) and computing
speed (-nlcom-).


On 01/05/2008, Stas Kolenikov <> wrote:
> If you
> can express WTP as the function of estimated parameters, then you
> should consider -nlcom- that would give you the delta method standard
> errors -- if you can technically do that, I would not bother with the
> bootstrap. You would probably find yourself wasting a week of your
> time setting your bootstrap up properly, to find the standard errors
> only differ in the third decimal point from those in -nlcom-.
*   For searches and help try:

*   For searches and help try:

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