Panel Data, correcting data for stationarity

[Karl Stehman]

Hello!
I have unbalanced panel data and was looking for stationarity with the fisher test. But i dont have. So i am looking for a solution, to get stationarity in my dependent (srisk) variable. So I built the differences and checked again.

. generate SRISK_Differenz = SRISK - SRISK-1
(408 missing values generated)

. xtunitroot fisher SRISK_Differenz, dfuller lags(0)
(408 missing values generated)

Fisher-type unit-root test for SRISK_Differenz
Based on augmented Dickey-Fuller tests

Ho: All panels contain unit roots Number of panels = 61
Ha: At least one panel is stationary Number of periods = 46

AR parameter: Panel-specific Asymptotics: T -> Infinity
Panel means: Included
Time trend: Not included
Drift term: Not included ADF regressions: 0 lags

Statistic p-value

Inverse chi-squared(122) P 0.0000 1.0000
Inverse normal Z . .
Inverse logit t(4) L* . .
Modified inv. chi-squared Pm -7.8102 1.0000

P statistic requires number of panels to be finite.
Other statistics are suitable for finite or infinite number of panels.

But that didnt help.

What can I do or did i something wrong?

Thank you very much!

[Jesse Wursten]

generate SRISK_Differenz = SRISK - SRISK-1

Have you checked what this variable looks like? Because I'm fairly sure you just created a variable of ones everywhere. I think the command you are looking for is

ge SRISK_difference = D.SRISK

[Karl Stehman]

Oh thank you very much! You are right! Now I have stationarity.
And now I have to repeat the other tests with srisk_difference, is that the way to go?

[Jesse Wursten]

I think so, but I'm no expert on stationarity requirements. I do know that sometimes it's okay to use non-stationary data, depending on the cointegration of your data.

[Johnny Cash]

Hi Karl, I am interested in the SRISK research lately. Is there any chance that u can share the code and data to compute SRISK? Thank u very much.

[Shakeel Sajjad]

Hi
I am working on MES and SRISK. Could you please share the codes and data to compute MES and SRISK? Thanks