Statalist


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

st: Not clear if I need to use -heckman- once or twice


From   Hugh Colaco <hmjc66@gmail.com>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   st: Not clear if I need to use -heckman- once or twice
Date   Mon, 30 Nov 2009 09:07:20 -0500

Hi,

This is the standard -heckman- example from the -help- menu using the
-twostep- procedure:-

webuse womenwk
heckman wage educ age, select(married children educ age) twostep

Suppose I want to take it one step further and predict the personal
wealth of women. This is not the best example, but it should be
somewhat clear as to what I am trying to achieve.

Let's assume "hours" (i.e. hours worked) is another variable in the
dataset and takes on a value only for women who earn a wage.

I then create an interaction term with "wage".

gen wagehrs = wage*hours

I need to run the following model:-

wealth = f(wage, hours, wagehrs, control variables)

I have data on the variable "wealth" and the control variables for
women who earn a wage AND women who don't.

Can someone please help me to model the above? Basically, I am not
clear if I need to run -heckman- once (as above) or twice? (ignore the
economic relevance or otherwise of the "wealth" regression since it is
merely for illustration purposes)

Thanks,

-- 
Hugh
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index