Statistics and Probability · Regression

Linear regression

Fitting a straight line that best predicts one variable from another, and reading its slope as an effect size.

Also known as: least squares, regression line, slope and intercept.

Start a lesson on Linear regression

Learn first

• Correlation: A single number summarizing how strongly, and in what direction, two variables move together.
• Point estimation: Using sample data to produce a single best-guess number for an unknown population value.

Leads to

• Multiple regression and model fit: Predicting an outcome from several variables at once, and judging how well the resulting model actually fits.

Related topics

• Multiple regression and model fit: Predicting an outcome from several variables at once, and judging how well the resulting model actually fits.