Statalist


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

RE: st: year dummy


From   "Rajesh Tharyan" <R.Tharyan@exeter.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: year dummy
Date   Fri, 28 Mar 2008 10:13:21 -0000

Maarten , carlo.. thanks for your replies.

Maarten, you have a point there on casuality, I will look up Austin's
article. Thanks for the reference.

Regards
rajesh





-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Maarten buis
Sent: 28 March 2008 08:43
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: year dummy

--- Rajesh Tharyan <R.Tharyan@exeter.ac.uk> wrote:
> I have a simple model, where I want to examine the effect of the
> regulation on certain behaviour. As far as the regulation is
> concerned, I want to look at two things. One is the enactment of the
> law (say year 2000) and the first enforcement of the law (say year
> 2004). Is it right to create dummy variables as below and run them in
> the same regression
> 
> gen enact= (year>2000)
> gen enfor= (year>2004)

Say the behavior is called y than your regression equation would look
like:

E(y) = b0 + b1 enact + b2 enfor

Prior to 2000 both enact and enfor are equal to zero, so:

E(y) = b0 + b1 0 + b2 0 = b0

That is, the expected amount of behavior y prior to enactment is b0

After enactment but prior to enforcement enact is 1 but enfor is 0, so:

E(y) = b0 + b1 1 + b2 0 = b0 + b1

So b1 is the decrease or increase in expected amount of y after
enforcement.

After enforcement both enact and enfor are 1:

E(y) = b0 + b1 1 + b2 1 = b0 + b1 + b2

So b2 is increase in expected y after enforcement after the act has
been enacted.

Notice that I have (tried to) avoid any reference to causality.
Societies change in many ways other than laws, and in this model all
these changes over time have been forced into these dummies. Moreover
you might want to think about the causal order: In my field
(educational reform) the law follows society instead of the other way
round, that is the law sanctions behavior after it has become so common
that it can no longer be ignored. In this case it is the behavior that
causes changes in the law instead of changes in the law causing changes
in behavior.

There is a nice article on this subject in the last Stata Journal:

Austin Nichols (2007) "Causal inference with observational data", The
Stata Journal, 7(4): 507--541.
http://www.stata-journal.com/article.html?article=st0136

Hope this helps,
Maarten




-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      ___________________________________________________________ 
Yahoo! For Good helps you make a difference  

http://uk.promotions.yahoo.com/forgood/
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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