Multiple Linear Regression Analysis Exam
Study Guide.
Multiple Linear Regression - Answer✔Regression model with multiple independent variables.
Regression Equation - Answer✔Mathematical representation of the relationship between
variables.
Dependent Variable (y) - Answer✔Outcome variable predicted by independent variables.
Independent Variables (x) - Answer✔Predictors used to estimate the dependent variable.
Regression Coefficients (β) - Answer✔Parameters estimated from data to fit the model.
Error Term (ε) - Answer✔Random error in the regression model.
Matrix Representation - Answer✔Compact form of regression using matrices.
Design Matrix (X) - Answer✔Matrix of independent variable values in regression.
Response Vector (y) - Answer✔Vector of observed values of the dependent variable.
Parameter Vector (β) - Answer✔Vector of regression coefficients.
Assumption of Errors - Answer✔Errors have mean zero and constant variance.
Least Squares Method - Answer✔Technique to estimate regression coefficients minimizing
errors.
Normal Equations - Answer✔Equations derived from least squares for parameter estimation.
Full Rank Condition - Answer✔Condition ensuring matrix X has maximum rank.
Variance of Errors (σ²) - Answer✔Constant variance of the error terms.
Forecasting - Answer✔Using regression to predict future values.
Compact Form - Answer✔Simplified representation of regression equations.
Observations (n) - Answer✔Number of data points used in regression analysis.
Rank of Matrix - Answer✔Maximum number of linearly independent column vectors.
Estimated Coefficients - Answer✔Values obtained from fitting the regression model.
1|Page
, ©Jason McConnel 2025 ALL RIGHTS RESERVED.
Random Errors - Answer✔Unpredictable variations in the dependent variable.
Regression Line - Answer✔Line that best fits the data points in regression.
Model Specification - Answer✔Formulating the correct regression model structure.
Least Squares Estimator - Answer✔Unbiased estimator for regression coefficients.
Residual Vector - Answer✔Difference between observed and predicted values.
Matrix Form - Answer✔Representation of equations using matrices.
Variance-Covariance Matrix - Answer✔Describes variance and covariance of estimators.
Gauss-Markov Theorem - Answer✔Best unbiased linear estimator among all unbiased
estimators.
Symmetrical Matrix - Answer✔Matrix equal to its transpose.
Idempotent Matrix - Answer✔Matrix that remains unchanged when squared.
Covariance - Answer✔Measure of how two variables change together.
Matrix Transpose - Answer✔Flipping matrix over its diagonal.
Data Frame - Answer✔Table-like structure in R for data storage.
Matrix Multiplication - Answer✔Combining matrices to produce a new matrix.
Unbiased Estimator - Answer✔Estimator with expected value equal to parameter.
Residuals - Answer✔Differences between actual and fitted values.
Symmetry in Matrices - Answer✔Property where matrix equals its transpose.
Expected Value - Answer✔Mean of a random variable's possible values.
Regression Coefficients - Answer✔Parameters that represent relationships in regression.
Data Import - Answer✔Loading data from external files into R.
Matrix Inversion - Answer✔Finding a matrix that, when multiplied, gives identity.
Linear Combination - Answer✔Sum of scalar multiples of vectors.
Variance of Residuals - Answer✔Measure of spread of residuals around zero.
Proof of Unbiasedness - Answer✔Demonstration that estimator's expected value equals true
value.
Covariance of Residuals - Answer✔Measure of relationship between residuals and estimators.
Trace of a matrix - Answer✔Sum of diagonal elements in matrix.
2|Page