Panel Data

[Zainab Mariam]

Question 1:

I tried to test for Stationary and applied the command ‘xtunitroot’ with the option ‘IPS’ as the data type of my research is unbalanced panel data, the time period is 20 years, annual data for more than 5000 firms. I typed in Stata the following: xtunitroot ips X1. Stata shows the following message: “no observations r(2000);”. Then, I typed in Stata the following: xtunitroot ips Y. Stata shows the following message: “insufficient observations r(2001);”. Thus, I kindly ask you please to highlight what I did wrong and what I should do.

Question 2:

Most of the explanatory variables in my model are lagged one year. What is the command to run this regression with some lagged explanatory variables?

Thank you in advance.

[Jared Greathouse]

Hey Zainab, go read the FAQ about how to ask a question, please.

[Maxence Morlet]

I'm not sure you can allow for a unit root with only 20 time periods, although I'm not sure

[Zainab Mariam]

Hello,
I am using Stata 2014.

Question 1:

I tried to test for Stationary for the dependent variable Y and for each explanatory variable included in my model. I applied the command ‘xtunitroot’ with the option ‘IPS’ as the data type of my research is unbalanced panel data, the time period is 22 years, annual data for 5084 firms. To test for Stationary for the dependent variable Y, I typed in Stata the following: xtunitroot ips Y. Stata shows the following message: “insufficient observations r(2001);”. To test for Stationary for the first explanatory variable X1, I typed in Stata the following: xtunitroot ips X1. Stata shows the following message: “no observations r(2000);”. Thus, I kindly ask you please to highlight what I did wrong and what I should do.

Question 2:

My model includes 10 explanatory variables where nine of them are lagged one year, while only one of these explanatory variables is in the current time/present period (i.e., not lagged. It is in time t). What is the command to run such a regression?

Thank you in advance.