Mindy: I am guessing that you are asking (1) how to run a regression with
lagged variables and (2) how to save the predicted values. You might
describe the SIC code; if you are using the four-digit code, implying
thousands of regressions, then you will need to use a loop. On the other
hand, if there are only a few industry differences that matter, then you
could use predict after your regressions.
Within SIC lags:
sort SIC
by SIC: gen CF_1=CF[_n-1]
by SIC: gen CF_2=CF[_n-2]
etc.
Residuals:
reg WC_1 CF_1 CF_2 CF if SIC==1
predict r_sic1, resid
etc.
estimates may also be useful to you see
man estimates
On Wed, 16 Nov 2005, Mindell Nitkin wrote:
:I am running a series of regressions on industry specific data,for example
:sort SIC
:by SIC: regress WCj,t-1 CFj,t-2 CFj,t-1 CFj, t
:
:The resulting coefficencts from the lagged industry regressions, need to
:be applied to current year values for each firm in the industry in order
:to predict the level of WCj,t and to calculate the residual which will
:be used in as an earnings quality metric in other regressions.
Caleb
caleb@uoregon.edu
University of Oregon Sociology
*
* 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/