|
To further develop the students knowledge of Linear Models.
Polynomials and factors in regression. Weighted least squares. Transformation of response and predictors, Box-Cox method, variance stabilizing transformation. Collinearity and variance inflation factors. Model selection: forwards, backwards and stepwise. All possible regressions, Mallow's Cp and PRESS. Cross-validation. Auto-correlation, Durbin-Watson test. AR(1) models. Linear mixed model theory, single random effects, multiple random effects, repeated measures, random coefficient models.
ST685 is equivalent to ST465 (i.e. lectures and tutorials as for ST465).
|