st: re: Re: Panel data and lagged dep variable

[Christopher Baum <kit.baum@bc.edu>]

<>
Hi Kit, as you indictaed "If you believe that it takes more than one of your
time periods for economic agents to adjust to changes in the Xs (or to
adjust to shocks), then the LDV is warranted." does that mean current value
of Y is closely related with previous value of Y? e.g company's current
income is closely related with previous income.

In a predictive sense, if the coeff on the LDV is not statistically distinguishable from zero, then current income is not closely related to previous income, cet.par. But the real question is whether a change in X causes income to change only in the current period or whether it has effects on subsequent periods. If it does, then something like a partial adjustment process is in order, and the LDV should be included.

You can't just look at the ACF of current income. 

KIt



Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   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/