Linear regression

From Wikiversity
Jump to: navigation, search

The first step to understanding linear regression is to make sure you understand linear correlation.

Regression examines the relationship between two variables by determining the line of best fit (on a scatterplot). The properties of this line of best fit are determined as the slope (b) and where it touches the Y-axis (a).

Regression involves:

  • A predictor (X) variable, or an independent variable (IV), shown on the X-axis
  • An outcome (Y) variables, or a dependent variable (DV), shown on the Y-axis
Example of a line of best fit for a linear regression (i.e., one dependent and one independent variable).

The generic equation for a simple linear regression is:

\hat Y  = bX + a
Linear regression variables and co-efficients indicated on a scatterplot with line of best fit.
Linear regression scatterplot with line of best fit and generic linear regression formula.

See also[edit]