This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: R 2 SST = 2 1 ) ( âˆ‘ =n i y y = total sum of squares for y (the response variable) SSR = 2 1 ) ( âˆ‘ = âˆ§n i y y = sum of squares for the regression SSE = 2 1 ) ( âˆ‘ = âˆ§n i y y = sum of the errors squared It can be mathematically shown that SST = SSR + SSE Define r 2 = SST SSR 2) Residual (error) Analysis a) Is the linear model reasonable b) Are the errors: i) normally distributed about the regression line ii) of constant variance for all x values 3) Influential observations  Influential points  points which when removed from the data will result in a significant change in the slope and/or intercept of the regression line Outliers  points outside the general pattern of data...
View
Full Document
 Fall '10
 RaySievers
 Statistics, Correlation, Regression Analysis, Scatter Plots, Scatter plot, regression line

Click to edit the document details