Dear all,
I am using modified LARS algorithm (ref: The Adaptive Lasso and Its Oracle
Properties, Zou 2006) for adaptive lasso penalized linear regression.
1. w(j) <- |beta_ols(j)|^(-gamma) gamma>0 and j = 1,...,p
2. define x_new(j) <- x(j)*w(j)
3. apply LARS to solve modified lasso problem
out.adalasso <- lars(X_new,y,type="lasso") or
enet(X_new, y,
lambda=0)
suppose, the estimated coefficients are beta_new(j), j=1,...,p
4. beta_adalasso <- beta_new(j)*w(j)
everything went fine except I am having problem in plotting standardized
(adaptive lasso) coefficients vs. |beta|/max(|beta|). It seems that
plot(out.adalasso) provides plot for beta_new. How can i get similar plot
for beta_adalasso.
--
View this message in context:
http://www.nabble.com/Plotting-problem--lars%28%29-elasticnet%28%29--tp24446187p24446187.html
Sent from the R help mailing list archive at Nabble.com.
