If the residuals in your regression are non-normal, a larger sample size might help improve the reliability of confidence intervals for Y.

Question

Quizplus · Accepted Answer

Larger sample sizes can invoke the Central Limit Theorem, which suggests that with a sufficiently large sample size, the distribution of the sample means (and by extension, other estimators like confidence intervals) will approximate a normal distribution, even if the residuals themselves are not normally distributed. This can improve the reliability of confidence intervals for predictions of Y.

If the Residuals in Your Regression Are Non-Normal, a Larger