Hello,
I may have a very naive question about panel data. I have data for every quarter of a large number of companies for 9 years. I'm researching the effect whether a change in an interest rate changes the volume of assets of these companies.
When I perform my panel data regression by using xtreg asset interest my result are very significant and the sign of the coefficient is as expected. However, after reading a lot of different literature it has come to my attention that one should check for unit roots. Unfortunately, I'm unsure if I should check for unit roots because my timespan is quite low and my number of companies is quite large (T=36 and N=600). Should I conduct a panel unit root test or can I ignore it?
I may have a very naive question about panel data. I have data for every quarter of a large number of companies for 9 years. I'm researching the effect whether a change in an interest rate changes the volume of assets of these companies.
When I perform my panel data regression by using xtreg asset interest my result are very significant and the sign of the coefficient is as expected. However, after reading a lot of different literature it has come to my attention that one should check for unit roots. Unfortunately, I'm unsure if I should check for unit roots because my timespan is quite low and my number of companies is quite large (T=36 and N=600). Should I conduct a panel unit root test or can I ignore it?