Hello everyone,
I have 50 time-series, for which I need to run a GARCH model for volatility forecasting. What I want to do is to avoid running each model seperately (red highlighted). Any ideas on how I could do that?
Many thanks in advance.
data data;
infile "C:\Users\kg25\Desktop\Test Data.txt" dsd dlm='09'x firstobs=2 lrecl=32767 stopover;
input date:ddmmyy. (a1-a50)(:numx.??);
format date ddmmyy10.;
run;
*Create Returns and Squared Returns;
data data2;set data;
vars(*) a1--a50;
array r(50);
do i=1 to dim(vars);
end; drop i;
var(*) r1--r50;
array rsq(50);
do i=1 to dim(var);
end; drop i;
run;
*create time variable;
data data2;set data2(firstobs=2);time + 1;
by date;
run;
*Choose in-sample;
data data3;set data2(obs=1303);
run;
*Create observations for 1 year;
data data4;
do time = 1304 to 1564;output;end;
run;
*merge data;
data data5;
merge data3 data4;by time;
run;
*Estimate AR(1)-Garch (1,1) model;
proc autoreg data=data5;
model r1= / nlag=1 garch=(q=1, p=1) maxit=50 noprint;
output out=data6 cev=vhat1;
run;
*merge data;
data data7;
merge data6 data2;by time;
run;
*Compute Mean Absolute Error and Root Mean Square Error;
data data8;set data7(firstobs=1304);
MAE=abs(rsq1-vhat1);
RMSE=sqrt(rsq1-vhat1);
run;
proc means data=data8 mean stderr prt;
var mae rmse;
run;
Transpose your data.
If you have for example r1-r50
data transpose_reg;
set data5;
array r(50) r1-r50;
do i=1 to 50;
reg_var=r(i);
output;
end;
drop r1-r50;
run;
Proc sort data=transpose_reg;
by i;
run;
proc autoreg data=transpose_reg;
BY i;
model reg_var= / nlag=1 garch=(q=1, p=1) maxit=50 noprint;
output out=data6 cev=vhat;
run;
Transpose your data.
If you have for example r1-r50
data transpose_reg;
set data5;
array r(50) r1-r50;
do i=1 to 50;
reg_var=r(i);
output;
end;
drop r1-r50;
run;
Proc sort data=transpose_reg;
by i;
run;
proc autoreg data=transpose_reg;
BY i;
model reg_var= / nlag=1 garch=(q=1, p=1) maxit=50 noprint;
output out=data6 cev=vhat;
run;
Many thanks Reeza! It worked in this way as well!
Join us for SAS Innovate April 16-19 at the Aria in Las Vegas. Bring the team and save big with our group pricing for a limited time only.
Pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.