This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: regression line to make predictions for values of the predictor variable that are much larger or much smaller than those observed. If you do so, you are making predictions outside the scope of the model. Don’t use values extremely different than those used to find the line. Example: We type of linear relationship do you think this data has? Negative correlation X 2 3 5 6 6 y 6 5 5 3 2 2 x y 6 5 4 3 2 1 6 5 4 3 2 Scatterplot of y vs x Find the leastsquares regression line. X Y X 2 Y 2 XY 6 36 2 5 4 25 10 3 5 9 25 15 5 3 25 9 15 6 2 36 4 12 6 2 36 4 12 ∑ x ∑ y ∑ x 2 ∑ y 2 ∑ xy Scatterplot w/ regression line. x y 6 5 4 3 2 1 7 6 5 4 3 2 Scatterplot of y vs x...
View
Full Document
 Fall '07
 MELutz
 Statistics, Correlation, Correlation Coefficient, Least Squares, Regression Analysis, leastsquares regression line

Click to edit the document details