This preview shows pages 1–2. Sign up to view the full content.

1. (a) The correlation will be closer to 1, as this observation clearly falls outside of the linear pattern of the remaining observations. (b) No the correlation would not change, as the correlation does not depend on the units of measurement. 2. The population size was also increasing, thus it would be expected that the number of crimes would increase as well. 3. (a) There is a moderately strong positive linear association between the two vari- ables. (b) The response variable ( y ) is relative mortality rate and the explanatory variable ( x ) is relative smoking rate. The slope is: b = r ± s y s x = 0 . 716 ± 26 . 1 17 . 2 = 1 . 0865 The intercept is: a = ¯ y - b ¯ x = 109 - 1 . 0865(103) = - 2 . 9095 The least-squares regression equation is: ˆ y = - 2 . 9095 + 1 . 0865 x (c) The predicted value is: ˆ y = - 2 . 9095 + 1 . 0865(110) = 116 . 6055 4. (a) False; points that lie above the least-squares regression line will have positive residuals. (b) True

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.