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 on April 23, and its replacement, statalist.org is already up and running.


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

st: dropped time variable


From   "Tirone, Vanessa" <vtirone@utk.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: dropped time variable
Date   Tue, 9 Apr 2013 01:47:06 +0000

Hello,

I am attempting to run a model with one independent variable and several control variables predicting a forward lagged variable. There is data on the predictors and outcome variables at baseline, 6 months, and 12 months. I was also planning on running another model containing an interaction term between the independent variable and time. However, in the first model the time variable is dropped from the model  due to collinearity. Is there a way to resolve this? Does it say something about the stability of  my variables over time?

Below is a copy of my syntax. The outcome variable is zcom.


reshape long Zcom Zalt Zinv Zsat Zphys Zpsyc Zsex Zinj, i(Participant) j(time)

tset Participant time
*forward lagged variables
g flZcom = f.Zcom
g flZalt = f.Zalt
g flZinv = f.Zinv
g flZsat = f.Zsat
g flZphys = f.Zphys
g flZpsyc = f.Zpsyc
g flZsex = f.Zsex
g flZinj = f.Zinj

gen inv_x_time = Zinv*time

xtreg flZcom Zcom Zinv time Zphys Zpsyc Zsex Zinj, pa corr(ind) robust

xtreg flZcom Zcom Zinv time inv_x_time Zsat Zalt Zphys Zpsyc Zsex Zinj, pa corr(ind) robust


Thank you,

Vanessa Tirone, M.A.

University of Tennessee

Clinical Psychology Doctoral Candidate 






*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index