STAB22H3 Chapter Notes - Chapter 8: True Value, Standard Deviation, Scatter Plot
38
STAB22H3 Full Course Notes
Verified Note
38 documents
Document Summary
Model a relationship with a line and its equation. Linear model: equation of a straight line through the data. Predicted value ( ) : estimated value made from a model; also called fitted value or fit. True value ( y ) : value on the graph. Residual: difference between the observed value and its associated predicted value. Tells us how far off the model"s prediction is at the point e = y residual = true value predicted value. A scatterplot of residual vs x-values should stretch horizontally with about the same scatter throughout. Standard deviation of residuals: se = e. The line of best fit is the line for which the sum of the squared residuals is the smallest, the least squares line. = b1x + b0 ( y = mx + b ) The least squares line: also called regression lines b1 = r sy sx.
