Forecasting using SAS Forecast Server, SAS/ETS, and more

Lagged dependent variable as input to the model

Accepted Solution Solved
Reply
Occasional Contributor
Posts: 8
Accepted Solution

Lagged dependent variable as input to the model

I am trying to introduce AR1 term into my models (lag of dependent variable). It is easy to do for the for the historic period which is lag(y). But I am wondering how to create it for the forecast period (it would actually be the lag of the prediction).  Is ther any SAS procedure or autoreg can do this??  My data looks like:

 

Date                                    Y                            lag(y)                    X1           X2

…                                          .006                      ….                        12           7

Q1 2016                              .005                      .006                      1             3             

Q2 2016                              .004                      .005                      11           7

Q3 2016                              .003                      .004                      8             7

Q4 2016                              .004                      .003                      10           6

Q1 2017                              .                             .004                      12           5

Q2 2017                              .                             .                             11           4

Q3 2017                              .                             .                             10           3

Q4 2017                              .                             .                             11           4

….

 

How do I populate lag(Y) for qtr’s Q2 2017 & beyond so that I can use it in regression??

 

Thanks in advance.


Accepted Solutions
Solution
a week ago
SAS Super FREQ
Posts: 79

Re: Lagged dependent variable as input to the model

Input Variables and Regression with ARMA Errors

You can use PROC ARIMA from SAS/ETS with p = 1 (AR1) along with x1 and x2 as input variables. 

proc arima data=<yourdata>; identify var=y crosscorr=(x1 x2); estimate p=1 input=(x1 x2); run;

View solution in original post


All Replies
Solution
a week ago
SAS Super FREQ
Posts: 79

Re: Lagged dependent variable as input to the model

Input Variables and Regression with ARMA Errors

You can use PROC ARIMA from SAS/ETS with p = 1 (AR1) along with x1 and x2 as input variables. 

proc arima data=<yourdata>; identify var=y crosscorr=(x1 x2); estimate p=1 input=(x1 x2); run;
Valued Guide
Posts: 797

Re: Lagged dependent variable as input to the model

You want a one period lead for Y.  I like @alexchien's answer, but here is a way to get a one period lead:

 

data need;

  merge have

             have (firstobs=2 keep=y rename=(y=y_lead1));

run;

☑ This topic is SOLVED.

Need further help from the community? Please ask a new question.

Discussion stats
  • 2 replies
  • 192 views
  • 0 likes
  • 3 in conversation