Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: set initial values for ml model


From   Maarten Buis <[email protected]>
To   [email protected]
Subject   Re: st: set initial values for ml model
Date   Mon, 19 Sep 2011 10:45:52 +0200

That depends on way too many things. You just need to find why the
matrix you think should contain the starting values, does in fact not
contain the starting values you need, and than adjust your program
accordingly.

-- Maarten

2011/9/18 健 张 <[email protected]>:
> Hi, all:
> I am trying to use ml to estimate a bivariate probit model so that I can set initial values myself. First, I use biprobit to estimate the two equations and then I got all coefficients stored in e(b). Then I use ml to write my own likelihood evaluator. I use the following code to set initial values:
> matrix b0=e(b)
> ml init b0
> However, stata always reports that " initial vector: extra parameter treated:connect1 found specify skip option if necessary". Treated is the dependent variable of my first equation and connect1 is a variable listed in both equations.
>
> In addition, anyone knows how to find a good initial value? Since I have around 20 independent variables in total in two equations, it is hard for me to fish the good initial value one by one.
>
> Thank you in advance!!
>
>
> Best,
> Jian
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>



-- 
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index