BookmarkSubscribeRSS Feed
Irene
Calcite | Level 5

I try to replicate the example 6.2 in Montgomery, Jennings and Kulahci's textbook. The dynamic regression model is: the error AR(1), transfer function w/1-delta1B-delta2B^2 and lag=3. After specifying

Y = P=( 1 )  NOINT  + x : LAG=3 DEN=( 1 2 )

in the SubsetARIMA model.

 

The results cannot be shown. It reads "The results of the current transformation cannot be shown in this type of plot".

 

Could anyone help? 

6 REPLIES 6
udo_sas
SAS Employee

Hello -

After creating this model using the Subset ARIMA dialog - do you see any messages in the LOG file?

The reason for failing to show plot is usually data dependent, so you might be better of contacting Technical Support.

Thanks,

Udo

Irene
Calcite | Level 5

Thanks for the timely reply. I have attached here the log file. So can you see where the problem is?

Besides, may I ask how to use FS do the prewhitening? Or, in general, is there a quick way that FS can help identify the specifications of dynamic regression model?

udo_sas
SAS Employee

Hello -

Yes, there are ERROR: messages at line 1861 (there may be more). Please contact Technical Support for additional help.

 

With regards to your second question: you will find details of how SAS Forecast Studio creates dynamic regression models automatically in SAS Forecast Server Procedures 14.1: User's Guide (check out details section of HPFDIAGNOSE procedure, covers prewhitening too).

 

Thanks,

Udo

alexchien
Pyrite | Level 9

I am not sure if the ID statement is specified correctly

id time interval=DTMINUTE format=TIMEAMPM11. acc=total notsorted horizonstart=&HPF_HORIZON_START start=&HPF_START;

 

Are you trying to forecast a series in the minutes interval? The input data contains 100 observations but the output appears to be 8 millions+ observations.

 

 

ERROR: Unable to allocate requested memory for time series meta-model _LEAF_3 for variable y.

WARNING: No model was chosen from the selection list for variable y. Now attempting to forecast using exponential smoothing.

WARNING: Unable to forecast the variable y. Forecast values set to missing.

NOTE: Number of series processed: 1

NOTE: Number of forecasts requested: 1

NOTE: Number of forecasts failed: 1

NOTE: There were 100 observations read from the data set _LEAF.DATA.

NOTE: The data set WORK.OUT has 8726411 observations and 2 variables.

NOTE: The data set WORK.OUTFOR has 8726411 observations and 8 variables.

Irene
Calcite | Level 5

I am using SAS Forecast Studio 13.1 for Desktop. So I cannot code and use any procedures? And, I cannot automatically get the dynamic regression model specifications and forecasting, right?

udo_sas
SAS Employee

Hello -

"I am using SAS Forecast Studio 13.1 for Desktop. So I cannot code and use any procedures?"

Correct.

"" And, I cannot automatically get the dynamic regression model specifications and forecasting, right?

You should see the automatic dynamic regression model specifications in model view.

Thanks,

Udo

sas-innovate-2024.png

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.

 

Register now!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 6 replies
  • 1554 views
  • 0 likes
  • 3 in conversation