Skip to content

Lasso Regression

Jump to bottom Edit New page
Ravi Teja Gudapati edited this page Oct 27, 2022 · 1 revision

Lasso Regression is used when there are more predictors (p) than observations (n).

Problems that arise due to having more predictors than observations:

  1. Calculating inverse of $X^TX$ (pxp) matrix to solve $\beta = (X^TX)^{−1}X^TY$ is not possible (singular)
  2. Over-fitting might occur due to multiple predictors being correlated to the dependent variable
Add a custom footer
Add a custom sidebar
Clone this wiki locally