Timeline for Lasso vs. adaptive Lasso

9 events

when toggle format	what		by	license	comment
Jan 25, 2017 at 14:06	comment	added	bdeonovic		good catch, its actually the penalty.factor argument
Jan 25, 2017 at 14:05	history	edited	bdeonovic	CC BY-SA 3.0	added 18 characters in body
Jan 24, 2017 at 18:55	comment	added	jmb		I think the weights argument in glmnet refers to weights for observations, and not weights for penalties
Aug 30, 2016 at 15:18	comment	added	Richard Hardy		@MrValidation, note that authors of new methods like adaptive lasso may have code for the method on their websites (sometimes they just give a reference to an R package that they themselves have written).
Aug 25, 2016 at 11:59	comment	added	Mr Validation		So basically, glmnet performs LASSO or elastic net by default, but you can switch this to adaptive LASSO (or EN) by specifying appropriate weights? If this is the case, thanks a million!
Aug 25, 2016 at 11:39	history	edited	bdeonovic	CC BY-SA 3.0	added 4 characters in body
Aug 25, 2016 at 11:28	comment	added	Marcel10		Small addition: The denominator of the weights should be the $\| \beta \|^{\gamma}$, $\gamma$ is often set equal to 1, but could also be estimated using cross validation. Furthermore, it is only valid to use the $\beta$ obtained from a root-n consistent estimator (but you're right, LASSO and LS can be used).
Aug 25, 2016 at 11:13	comment	added	Richard Hardy		You forgot to take absolute values in the penalty terms.
Aug 25, 2016 at 10:56	history	answered	bdeonovic	CC BY-SA 3.0