After you have taught bivariate linear regression (a two parameter model, intercept and slope) to your students, stressing the least squares criterion, you may want to point out that the mean is simply the intercept in a single parameter linear model, that is, predicted Y = mean Y. The variance is then just the MSE (residual variance) for that model and the standard deviation is just the standard error.
Once your students have grasped the idea that the mean is a single point in one dimensional space that minimizes the SS about it, and that a regression is defined in the same way in two dimensional space, you have them primed for the leap to multiple regression and all of its special cases (like ANOVA) and elaborations. Karl W. ----- Original Message ----- From: "jim clark" <[EMAIL PROTECTED]> To: "Teaching in the Psychological Sciences" <[EMAIL PROTECTED]> Sent: Tuesday, February 25, 2003 12:56 PM Subject: Re: SD Woes For example, the M is the center of a distribution in the sense that the sum of squared deviations about the mean (SS) is a minimum. Jim --- You are currently subscribed to tips as: [EMAIL PROTECTED] To unsubscribe send a blank email to [EMAIL PROTECTED]
