s-news
[Top] [All Lists]

application of ridge to all predictors

To: s-news@lists.biostat.wustl.edu
Subject: application of ridge to all predictors
From: carol white <wht_crl@yahoo.com>
Date: Sun, 17 Jun 2007 01:33:09 -0700 (PDT)
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=2YnzR/skJdHRJLzBfUHdM/GYVL06HTkhxjMPSR76xuoVE+mDaNQa003Ne/bL5ehlAjamNaqaO3WPnsNdExqNI84pcquo2kqiF8YAc6K1Xmboan10Ch+nRig189I9qMC37BBU11ywFGPrKzcN0uohiy9pbrKKBXWdtHqUyTNg5Es=;
Hi,
It might be a primitive question but how do you specify all predictors in ridge function?
suppose that I have 100 predictors and I want to apply ridge to all 100 variables. instead of putting the name of all variables separated by "," (see 2nd code line below),  which notation should I use so that ridge would be applied to all variables?

usage of ridge function
ridge(..., theta, df=nvar/2, eps=0.1, scale=TRUE)
fit1 <- coxph(Surv(futime, fustat) ~ rx + ridge(age, ecog.ps, theta=1),
              ovarian)


Luggage? GPS? Comic books?
Check out fitting gifts for grads at Yahoo! Search.
<Prev in Thread] Current Thread [Next in Thread>
  • application of ridge to all predictors, carol white <=