Subset selection is used to identify a subset of the predictors and then fit a model using least squares on the reduced set of variables.

Subset selection is used to identify a subset of the predictors and then fit a model using least squares on the reduced set of variables.

• A. True
• B. False
• C. Sometimes
• D. Never

Answer: (A)

Subset selection is a two-step process: first choose a subset of predictors to include in the model, then estimate the coefficients using ordinary least squares on that reduced set. Once the predictors are fixed, ordinary least squares provides the best linear fit for that design matrix, minimizing the residual sum of squares and giving unbiased, efficient estimates under the standard regression assumptions. This combination—selecting a smaller set of variables and then fitting with least squares on that set—is the standard approach, so the statement is true. While there are alternative methods that blend selection and estimation, the described procedure reflects the traditional subset selection framework.

Subset selection is a two-step process: first choose a subset of predictors to include in the model, then estimate the coefficients using ordinary least squares on that reduced set. Once the predictors are fixed, ordinary least squares provides the best linear fit for that design matrix, minimizing the residual sum of squares and giving unbiased, efficient estimates under the standard regression assumptions. This combination—selecting a smaller set of variables and then fitting with least squares on that set—is the standard approach, so the statement is true. While there are alternative methods that blend selection and estimation, the described procedure reflects the traditional subset selection framework.