Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

st: Least square regression involving time lags in the parameters


From   "Lodh Ashish" <Ashish.Lodh@Generali.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Least square regression involving time lags in the parameters
Date   Tue, 13 Jul 2010 14:09:52 +0200

Dear all,

I am trying to model a regression on a dependent variable using 6
independent parameters.
All these variables are time series sampled at identical time intervals.
I have the independence to lag the 6 parameters individually by 0 to 10
time steps in order to get a better fit.
My aim is to find the best fit (with significantly low p-values for the
betas) of regression by using different lags on the parameters.
For example, I might get the best fit (say adjusted R-square of 94%)
using the lags 0, 2, 0, 5, 5, 1 respectively on the six variables.

I made a program in MATLAB using nested loops and it works fine. The
only problem being large number of OLS regressions take a long time to
compile.
I wish to do the same in Stata. Can anybody throw some light on how it
can be done in Stata?
I hope there is a simpler process in Stata to do the same.

Thanks
Ashish



*
*   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   |   Site index