BookmarkSubscribeRSS Feed
Jonison
Fluorite | Level 6

Hello, I am building a very customized model in SAS, and requires PLS procedure.

 

The issue is that the X variables have a complicated structure and requires individual data pre-treatment, and this has been done using separate codes. The Y variables consist of a set of responses which are using standard pre-treatment.

 

Currently, I am using the statement below, where the pre-treatment of X and Y variables has been supressed. The issue for this is that the predicted results are the prediction that has been 'pre-treated'.

 

 

PROC PLS CV=ONE DATA=&EM_IMPORT_DATA METHOD=PLS NOCENTER NOSCALE NFAC=6 MISSING=AVG;
 MODEL &Y1 = &X1 &X2 &X3 &X4 &X5 &X6 &X7 &X8 &X9 &X10 &X11 &X12 &X13;
 ODS output ParameterEstimates=Parm;
 OUTPUT out=plsout p=p1 p2 p3 p4 p5;
QUIT;

 

 

 

Can I have some advice that if the PLS procedure can do the pre-treatment separately for X and Y variables, e.g. supress X variables pre-treatment while standardize Y variables.

 

Many thanks for your kind help on this.

 

 

 

3 REPLIES 3
PaigeMiller
Diamond | Level 26

Please define what you mean by "pre-treatment".

--
Paige Miller
Jonison
Fluorite | Level 6
In this example, it is standardize.
Thanks
PaigeMiller
Diamond | Level 26

@Jonison wrote:


Can I have some advice that if the PLS procedure can do the pre-treatment separately for X and Y variables, e.g. supress X variables pre-treatment while standardize Y variables.


If you want to standardize X and Y separately, where X is not standardized while Y is standardized, this would have to be done using code to modify the data appropriately before PROC PLS runs. Then in PROC PLS you would use the NOCENTER and NOSCALE options.

 

Please note that if you don't standardize the X variables, the variables with larger variances will tend to have larger effects in prediction (which may be the right thing to do in some applications, but the wrong thing to do in other applications).

--
Paige Miller

SAS Innovate 2025: Save the Date

 SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!

Save the date!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 3 replies
  • 574 views
  • 2 likes
  • 2 in conversation