The standard error of estimate is used to construct confidence intervals when the sample size is large and the scatter about the regression line is somewhat normally distributed.

Question

Quizplus · Accepted Answer

This is correct. The standard error of estimate is a measure of the variability of actual y values around the predicted y values. When the scatter of the residuals is somewhat normally distributed, the standard error of estimate can be used to construct confidence intervals for the population values. However, when sample size is small, the distribution of the standard error of estimate will be skewed, and it will be less reliable for constructing confidence intervals.

The Standard Error of Estimate Is Used to Construct Confidence