Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 1 down vote favorite

Is there an R package for constrained regression, that has both a formula interface and a predict method? Two existing options are pcls from mgcv and nnls from nnls, but neither one appears to have a formula interface or a predict method.

share|improve this question
2  
Isn't one answer apparent at stats.stackexchange.com/questions/30565/…? – whuber♦ Jul 19 '12 at 19:02
1  
@whuber indeed, mgcv seems to be the package I am looking for (I wish it had a formula interface though!). Thank you. – Zach Jul 19 '12 at 19:06
For future reference: often such information can be found by searching our site. I found that link with a search on "+constrained +regression". By adjoining "+[r]" I found the duplicate question. – whuber♦ Jul 19 '12 at 19:10
@whuber Thank you. I swear I searched the site, but I don't know how I missed the top result. I just came across the nnls package as well. Both mgcv and nnls solve my problem, but I wish there was a slightly friendlier package, with a formula interface and predict methods. I suppose I can write my own wrapper functions. – Zach Jul 19 '12 at 19:13
Zach, with this improved information in hand, you have the basis to reopen your question: it now exhibits effective research, partial progress towards your goal, and a more definite focus. Why don't you incorporate your last comment as an edit and re-open the question? – whuber♦ Jul 19 '12 at 19:23
show 6 more comments

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.