Can you please help me on this below error:-
WARNING: Exact fit. No residual in model to analyze.
NOTE: The above message was for the following BY group:
Terminal=Hamar postterminal prodgrservniva=10 prodgrformat=Små
WARNING: Exact fit. No residual in model to analyze.
NOTE: The above message was for the following BY group:
Terminal=Hamar postterminal prodgrservniva=10 prodgrformat=Store
WARNING: Exact fit. No residual in model to analyze.
NOTE: The above message was for the following BY group:
Terminal=Hamar postterminal prodgrservniva=10 prodgrformat=Klump
ERROR: Floating Point Overflow.
ERROR: Termination due to Floating Point Exception
NOTE: The SAS System stopped processing this step because of errors.
Below is the code i am using:-
PROC AUTOREG DATA=prognose noprint;
by terminal prodgrservniva prodgrformat;
MODEL ant_sendinger=
man tir ons tor fre lor son
rompaske1 rompaske2 rompaske3 romjul
fellesferie skoleferie
hel_for_arb jul_ny_aften helg_f_jul
arb_etter_hel trend1 trend2
/NLAG=2 NOINT method=ml
;
OUTPUT OUT=res_prognose
p=antallhat pm=antalltrend r=residind lcl=lcl ucl=ucl alphacli=0.20;
RUN;
Thanks,
Daman
Without greater information, I would assume the ERROR message is telling me that the model overfits the data for those by groups. I would guess that there are 20 or fewer observations for those groups, thus resulting in an exact fit, and no residual error. Without additional info, this is as close a guess as I can hazard.
Steve Denham
agreed. When I saw the list of independ variables, the first thing in mind is possible over-fitting. It might be more than over-fitting in his case.
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
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.