Elastic net coefficents

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

paolo.zanghieri
Posts: 49
Joined: Wed Mar 05, 2014 10:52 am

Elastic net coefficents

Postby paolo.zanghieri » Wed Oct 21, 2020 3:31 am

Hi,
I am estimating a forecasting model using a large number of data. I am trying the Elastic Net. If I understand it correctly, if you standardize the regressors, the coefficents should be bounded between -1 and 1 (excluded). I get in several instances much bigger (in abs. value) coefficients. I copy below the settings, am I missing something?
thanks

Dependent Variable: LDR12USALL
Method: Elastic Net Regularization
Date: 10/21/20 Time: 12:23
Sample (adjusted): 2000M01 2019M07
Included observations: 235 after adjustments
Penalty type: Elastic Net (alpha = 0.5)
Lambda at minimum error: 0.1668
Regressor transformation: Std Dev (smpl)
Cross-validation method: K-Fold (number of folds = 5), rng=mt,
seed=198892710

EViews Rebecca
EViews Developer
Posts: 113
Joined: Thu Apr 18, 2013 8:37 am

Re: Elastic net coefficents

Postby EViews Rebecca » Wed Oct 21, 2020 10:35 am

The standardization of regressors refers to standardizing before the regression. It's not a constraint on the values of the coefficients.


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 46 guests