Iteratively re-weighted least squares for logistic regression re-examined: coping with nonlinear transformations and model-dependent heteroskedasticity. The common pattern of generalized linear models and IRWLS. Binomial and Poisson regression. The extension to generalized additive models.
Extended example: building a weather forecaster for Snoqualmie Falls, Wash., with logistic regression. Exploratory examination of the data. Predicting wet or dry days form the amount of precipitation the previous day. First logistic regression model. Finding predicted probabilities and confidence intervals for them. Comparison to spline smoothing and a generalized additive model. Model comparison test detects significant mis-specification. Re-specifying the model: dry days are special. The second logistic regression model and its comparison to the data. Checking the calibration of the second model.
Reading: Notes, chapter 13
Faraway, section 3.1, chapter 6, chapter 7
Posted at February 28, 2013 10:30 | permanent link