Unit roots and Cointegration Test for Panel Data
Posted: Fri Jul 31, 2009 2:54 pm
Hi Everyone,
I'm analyzing panel data for the first time and I'm not exactly sure if I'm doing anything right.
I've tested for panel unit roots. My dependent variable and a few of my independent variables are stationary. However, I have a few other independent variables which are I(1). I also have another variable which is stationary after differencing and adding trend. Does that count as an I(1) process?
Also assuming that those few independent variables are all I(1) and the rest are I(0). What sort of Cointegration test should I be looking at? I've considered the Pedroni Cointegration test but I'm not sure if that's the right thing to do. Also I'm not sure which variables I should include into the test considering that I have 8 variables in total and only 7 can go into the test.. I have 4 stationary variables including the dependent variable and 4 I(1) independent variables.
If anyone could lead me in the right direction, that would be fantastic. Thank you! :D
I'm analyzing panel data for the first time and I'm not exactly sure if I'm doing anything right.
I've tested for panel unit roots. My dependent variable and a few of my independent variables are stationary. However, I have a few other independent variables which are I(1). I also have another variable which is stationary after differencing and adding trend. Does that count as an I(1) process?
Also assuming that those few independent variables are all I(1) and the rest are I(0). What sort of Cointegration test should I be looking at? I've considered the Pedroni Cointegration test but I'm not sure if that's the right thing to do. Also I'm not sure which variables I should include into the test considering that I have 8 variables in total and only 7 can go into the test.. I have 4 stationary variables including the dependent variable and 4 I(1) independent variables.
If anyone could lead me in the right direction, that would be fantastic. Thank you! :D