Panel Data Regressions

[raqthesolid]

Hi Folks

i have panel data. Cross sectional Variable=id, Time series variable is t, when i try to run the panel regression using the following statement;

proc sort data=bank.mergid1; by id t; run;

proc panel data=mergid1;

id id t;

model ROAA=MS CR NIM SIZE EQTA OHTA OBSTA LG DC STTR/pooled;

run;

then following lines appear in log

370  proc panel data=bank.mergid1;

371  id id t;

372  model ROAA=MS CR NIM SIZE EQTA OHTA OBSTA LG DC STTR/pooled;

373  run;

ERROR: There is only one cross section or time series observation. Computations will be terminated.

NOTE: The SAS System stopped processing this step because of errors.

NOTE: PROCEDURE PANEL used (Total process time):

      real time           0.32 seconds

      cpu time            0.32 seconds

Note: my sas data file is attached
Regards

[raqthesolid]

Please somebody help if can  . THnaks

[Ksharp]

I only know how to do it in REGRESSION.

proc reg;

mode y=x1 x2... / vif ;

run;

check variance inflated factor , if variables'vif gt 10 then it has muliti-linear correlation .

or you can use proc corr to plot it correlated matrix graph and check their muliti-linear correlation .

I suggest you post it at  Steve might give you right answer.

SAS Statistical Procedures  

or

SAS Forecasting and Econometrics

since it is a statistical problem and it is about economic model .

Xia Keshan

[raqthesolid]

Thanks man but i want to create an ID variable from bank column ??how to do this ...

Regards

[Reeza]

Post your log with the error message.

[raqthesolid]

hi

when i use the following codes;

proc sort data=mergid1; by id t; run;

proc panel data=mergid1;

id id t;

model ROAA=MS CR NIM SIZE EQTA OHTA OBSTA LG DC STTR/pooled;

run;

then these are the line that appear when i try to run the Panel data regression.

370  proc panel data=bank.mergid1;

371  id id t;

372  model ROAA=MS CR NIM SIZE EQTA OHTA OBSTA LG DC STTR/pooled;

373  run;

ERROR: There is only one cross section or time series observation. Computations will be terminated.

NOTE: The SAS System stopped processing this step because of errors.

NOTE: PROCEDURE PANEL used (Total process time):

      real time           0.32 seconds

      cpu time            0.32 seconds

kindly help me to solve this issue. thanks

[Tom]

Not familiar with PROC PANEL but the message seems be saying that you do not have multiple time values. So the value of the variable T is constant.

[raqthesolid]

how can i make T as time series i tried everything i can but still it gives this message i uploaded a new data set. i will be very thankful if you can help me

Regards

[gergely_batho]

1. Eliminate countries (ids) where you have only one observation (one time period).

2. Then eliminate duplicate id t combinations.

proc sort data=bank.mergid1 out=mergid1 NOUNIQUEKEY; by id; run;

proc sort data=mergid1 out=mergid1 NODUPKEY; by id year; run;

proc panel data=mergid1;

...

[Tom]

So the variables you listed in your MODEL statement are not in the dataset you posted.