Renowned statistician R.G. Miller set the pace for statistics students with Beyond ANOVA: Basics of Applied Statistics. Designed to show students how to work with a set of "real world data," Miller's text goes beyond any specific discipline, and considers a whole variety of techniques from ANOVA to empirical Bayes methods; the jackknife, bootstrap methods; and the James-Stein estimator.
This reissue of Miller's classic book has been revised by professors at Stanford University, California. As before, one of the main strengths of Beyond ANOVA is its promotion of the use of the most straightforward data analysis methods-giving students a viable option, instead of resorting to complicated and unnecessary tests.
Assuming a basic background in statistics, Beyond ANOVA is written for undergraduates and graduate statistics students. Its approach will also be valued by biologists, social scientists, engineers, and anyone who may wish to handle their own data analysis.
Normal Theory
Nonnormality
Effect
Dependence
Exercises
Two Samples
Normal Theory
Nonnormality
Unequal Variances
Dependence
Exercises
One-Way Classification
Fixed Effects
Normal Theory
Nonnormality
Unequal Variances
Dependence
Random Effects
Normal Theory
Nonnormality
Unequal Variances
Dependence
Exercises
Two-Way Classification
Fixed Effects
Normal Theory
Nonnormality
Unequal Variances
Dependence
Mixed Effects
Normal Theory
Departures from assumptions
Random Effects
Normal Theory
Departures from Assumptions
Exercises
Regression
Regression Model
Normal Linear Model
Nonlinearity
Nonnormality
Unequal Variances
Dependence
Errors-in-Variables Model
Normal Theory
Departures from Assumptions
Exercises
Ratios
Normal Theory
Departures from Assumptions
Exercises
Variances
Normal Theory
Nonnormality
Dependence
Exercises
Biography
Rupert G. Miller Jr., University of Stanford, California, USA.