Introduction to Linear and Logistic Regression

In regression, a single dependent, or outcome variable is predicted using one or more independent variables. Use cases for regression are included, but are not limited to predicting:

• The win percentage of a team, given a variety of team statistics
• The risk of heart disease, given family history and a number of physical and psychological characteristics
• The likelihood of snowfall, given several climate measurements

Linear and logistic regression are popular choices for predicting such outcomes due to the ease and transparency of interpretability, as well as the ability to extrapolate to values not seen in the training data. The end goal of linear regression is to draw a straight line through the observations that minimizes the absolute distance between the line and observations (that is, the line of best fit). Therefore, in linear regression, it is assumed that the relationship between the feature(s) and the continuous dependent...