Is it useful to use sparse regression (e.g. Lasso) when the number of observations is significantly larger than the number of covariates?

by Ijies   Last Updated May 16, 2019 04:19 AM

I'm learning about penalized/sparse regression and I noticed that the examples used for penalized/sparse regression, e.g. Lasso, are usually cases where the number of observations is significantly smaller than the number of covariates/independent variables/predictors, $n << p$.

I was wondering if it would still be useful to apply such methods to datasets where we also have a large number of $p$ but the number of observations $n$ is significantly larger, $n >> p$.

For reference, we have a dataset that has $n = 19,051$ observations and each observation has $p = 336$ predictors.



Related Questions


Updated June 13, 2015 15:08 PM

Updated October 22, 2017 15:19 PM

Updated July 07, 2016 08:08 AM

Updated March 19, 2017 10:19 AM