STAB22H3 Chapter Notes - Chapter 8: Scatter Plot, Simple Linear Regression, Sample Size Determination
38
STAB22H3 Full Course Notes
Verified Note
38 documents
Document Summary
Chapter 8: linear regression finding the best line (p. 198) In math, straight line relationship looks like y=a+bx where x and y are variables, and a and b are numbers that describe what kind of straight line you have. A = intercept : value of y when x=0. Slope=2: increasing x by 1 increases y by 2. Slope=-3: increasing x by 1 decreases y by 3. Slope could be negative, if line goes downhill. If you know the intercept and slope, you know the straight line. Predicted/ fitted value (y") -> estimate made from a model. Residual-> difference between observed value and predicted value; tells how far off the model"s prediction e. g. go back to drug abuse data set. England"s actual drug use was 21, higher than predicted by the model: residual=y y"=21 17=4. *negative residual -> x units less than the model predictions.
