Multiple regression is a statistical technique that includes:

• A. Two or more predictor variables in a prediction equation
• B. Only one predictor variable
• C. A comparison of group means
• D. A non-parametric ranking method

Answer: (A)

Two or more predictor variables in the prediction equation. Multiple regression extends simple regression by using several independent variables to predict a dependent variable. Each predictor has its own coefficient, showing its unique relationship with the outcome while the other predictors are held constant. The usual form is Y = intercept + b1X1 + b2X2 + ... + error, illustrating how changes in each predictor contribute to changes in Y. You can combine continuous predictors with dummy-coded categorical predictors, and the model’s overall fit is often summarized with R-squared, which tells you how much of the outcome’s variance the predictors explain. Inference relies on assumptions like linear relationships, independent observations, homoscedastic residuals, and normally distributed residuals for valid hypothesis tests and confidence intervals.

Using just one predictor describes simple regression, a comparison of group means corresponds to ANOVA, and non-parametric ranking methods do not form a prediction equation with multiple predictors.