STAB22H3 Chapter Notes - Chapter 9: Confounding, Scatter Plot
38
STAB22H3 Full Course Notes
Verified Note
38 documents
Document Summary
Linearity assumption: we should not see a pattern on a scatterplot of residuals vs. ____ but instead there should be bend (starting high on the left, dropping down in the middle of the plot and going back up at the right) Including/ not including an outlier can have a big impact on residuals, leverage and influence. Large residuals are caused if the outlier"s y-value is far from the predicted y- value. High leverage is caused by the outlier having a x-value far from the mean of. An outlier is influential if by removing it the line of best fit/ model is changed the x-values (image above) One variable does not cause the other. Lurking variable: variable that may be causing the trend ; there is no way to be sure that a lurking variable is not the cause of any apparent association. A prediction of a value in a x-value territory that is not shown.
