W7 Regression

Regression

A statistical method that allows researchers to predict scores on one variable (the criterion) based on scores from another variable (the predictor).

Standard error of the estimate

A measure of how accurate the regression line is at predicting actual data points. It reflects the average distance that observed values fall from the regression line. Smaller values indicate more accurate predictions.

Covariate

A variable that is statistically controlled for in an analysis because it may influence the relationship between the predictor and criterion variables. It is often included to reduce error and isolate the effect of interest.

Extrapolation

Making predictions about the criterion variable using the regression equation outside the range of observed data. This is risky because the relationship may not hold beyond the collected data.

Bivariate regression

A regression analysis with one predictor variable and one criterion variable.

Multiple regression

A regression analysis with two or more predictor variables used to predict scores on one criterion variable.

Predictor variable

The variable or variables used to estimate or predict the criterion. It is the independent variable in regression.

Criterion variable

The outcome being predicted in regression. It is the dependent variable.

Y hat

The estimated or predicted value of the criterion variable based on the regression equation.