topic Re: how to use differencing in PANEL or HPPANEL procedure in Statistical Procedures

how to use differencing in PANEL or HPPANEL procedure

SJK_KOR — Tue, 18 Aug 2020 02:58:23 GMT

The Y variable is accumulated data.

I am trying to use differencing method using PROC PANEL or PROC HPPANEL procedure to analyse annually panel data by one-way random effect model.

I found out that differencing method can be used by PROC ARIMA. However, i would like to use PANEL or HPPANEL procedure.

Re: how to use differencing in PANEL or HPPANEL procedure

ChrisNZ — Tue, 25 Aug 2020 00:27:43 GMT

Moved to stats community.

Re: how to use differencing in PANEL or HPPANEL procedure

SteveDenham — Tue, 25 Aug 2020 12:08:52 GMT

I don't know what your MODEL statement looks like, but the FDONE option for the model statement does a one-way fixed effects fit to the differences and FDONETIME does a one-way fixed effects fit to the differences in time. These are available in PANEL but not HPPANEL, so far as I can tell.

SteveDenham

Re: how to use differencing in PANEL or HPPANEL procedure

SJK_KOR — Tue, 25 Aug 2020 12:23:14 GMT

Thanks for reply!

I was using RANONE and WK option to use One-way random effect.

Are FDONE or FDONETIME for one-way random effect? My model is cross sectional time series with one-way random effect.

Re: how to use differencing in PANEL or HPPANEL procedure

SteveDenham — Tue, 25 Aug 2020 12:33:03 GMT

It doesn't appear that this applies to a one-way random effects model.

However, I think you can get what you want in a 3 step process. PANEL supports a variety of LAG functions. What about:

Run PROC PANEL with the appropriate LAG and output the dataset. No MODEL statement in this run.

In a DATA step, calculate the differenced values using the original value and the lagged value in this output dataset.

Run PROC PANEL with a RANONE option for the MODEL statement on the differenced values.

Now, I have never done this, so take it with a great big shovel of salt. However, the LAG statement in PROC PANEL says that it is capable of handling panel data correctly. It would then be a matter of selecting the right version of the LAG statement to handle missing values.

SteveDenham