Goal of the project was to outline what linear model regressions can do. I took a dataset available on Kaggle, and specifically focused on closing price and volume of stocks traded. While this project mainly focused on fitting a simple linear regression, it did point me to other models that may better fit the dataset and can be explored in the future to find the best fit.

Practice with ioslides

Sure! Here's a concise 4-sentence summary: Linear model selection involves identifying a subset of predictors that best explains the response variable, balancing model complexity and predictive accuracy. Methods like best subset selection, forward selection, and backward elimination help choose the most relevant variables. Regularization techniques such as ridge regression and the lasso improve model performance by introducing a penalty on the size of coefficients to reduce overfitting. While ridge shrinks all coefficients toward zero, the lasso can force some to be exactly zero, thus performing variable selection as well.

DATA 622 Assignment 3