Principal Components Regression

Accepted Solution Solved
Reply
Occasional Contributor
Posts: 6
Accepted Solution

Principal Components Regression

Hello to everyone,

 

I have carried out principal components regression using the PROC PLS procedure with 'method=pcr'. I have concluded that the number of principal componentns to keeo is 2.

 

My question is:

 

Can I derive a model for my response variables and the 2 principal components I have found? If yes, waht is the command I should use in order to derive the coefficients for each PC? I have the intercept of the model.

 

Regards,

George


Accepted Solutions
Solution
‎02-22-2018 06:26 AM
Respected Advisor
Posts: 3,018

Re: Principal Components Regression

The SOLUTION option in the model statement will give you the model terms.

 

As a side issue, it was never clear to me why PCR was an option in PROC PLS, as the two component PLS model should always fit as well or better than the two component PCR model. 

--
Paige Miller

View solution in original post


All Replies
Solution
‎02-22-2018 06:26 AM
Respected Advisor
Posts: 3,018

Re: Principal Components Regression

The SOLUTION option in the model statement will give you the model terms.

 

As a side issue, it was never clear to me why PCR was an option in PROC PLS, as the two component PLS model should always fit as well or better than the two component PCR model. 

--
Paige Miller
Occasional Contributor
Posts: 6

Re: Principal Components Regression

Posted in reply to PaigeMiller

The thing is that I have to carry out different methods of Modern regression with a data set where the predictors are highly collinear. I have also carries Partial Least Squares Regression and the objective is to compare the different kinds of regression. 

 

Hope this clears your question.

 

--

George

Respected Advisor
Posts: 3,018

Re: Principal Components Regression

It's kind of hard for me to accept that PCR is a "modern" regression method, I would claim it is an antique method that should not be used in the 21st century. Nevertheless, you might want to take a look at the paper by Frank and Friedman, who did such a comparison of many different regression methods.

--
Paige Miller
Occasional Contributor
Posts: 6

Re: Principal Components Regression

Posted in reply to PaigeMiller

I totally understand what you are saying but I only follow orders here. Nevertheless thank you for your advice.

 

George

Smiley Happy

Super User
Posts: 23,724

Re: Principal Components Regression

but I only follow orders here

I didn't think AI had come that far...

 

☑ This topic is solved.

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

Discussion stats
  • 5 replies
  • 103 views
  • 0 likes
  • 3 in conversation