Which of the following is not an iterative variable selection procedure?

Best-subsets regression is not typically characterized as an iterative variable selection procedure. Instead, it involves evaluating all possible combinations of predictors and selecting the model with the best overall fit based on a criterion such as adjusted R-squared, AIC, or BIC. This complete examination of models does not iterate through a process of adding or removing variables based on their significance; rather, it assesses a comprehensive set of models to determine the best one at once.

In contrast, other options, such as stepwise regression, backward elimination, and forward selection, employ iterative approaches to build a model. Stepwise regression begins with no predictors and adds or removes them based on significance levels, while backward elimination starts with all predictors and removes the least significant ones iteratively. Forward selection adds the most significant predictors one at a time until a stopping criterion is met. These approaches depend on the incremental addition or subtraction of variables, which is characteristic of iterative processes.