This preview shows page 1. Sign up to view the full content.
Unformatted text preview: xy = ∑ i i y x ( ∑ i x )( ∑ i y )/n = 660.130  (205.4)(35.16)/11 = 3.5969. Therefore, b = SS xy /SS xx = 3.5969/44.7018 = .0805 and a = (35.16/11)  (.0805) (205.4/11) = 1.6932. The least squares line is then y ˆ = 1.6932 + .0805x. (b) Predicting speed from stride rate means that y = speed and x = stride rate. Therefore,interchanging the x and y subscripts in the sums of squares computed in part (a), we now have SS xx = .2969 and SS xy = 3.5969 (note that SS xy does not change when the roles of x and y are reversed). The new regression line has a slope of b = SS xy /SS xx = 3.5969/.2969 = 12.1149 and an intercept of a = (205.4/11)  (12.1149)( 35.16/11) = 20.0514; that is, y ˆ = 20.0514 + 12.1149x....
View
Full
Document
This document was uploaded on 05/15/2010.
 Spring '08
 Least Squares

Click to edit the document details