This is the first text in a generation to re-examine the purpose of the mathematical statistics course. The book's approach interweaves traditional topics with data analysis and reflects the use of the computer with close ties to the practice of statistics. The author stresses analysis of data, examines real problems with real data, and motivates the theory. The book's descriptive statistics, graphical displays, and realistic applications stand in strong contrast to traditional texts that are set in abstract settings.

Benefits:

• NEW! Nearly 100 new problems, including many that are substantial enough to form the basis for computer labs.
• NEW! Examples from contemporary, high interest areas such as genomics and financial statistics complement already interesting existing applications (e.g., probability of AIDS infection, state lotteries, polygraph testing) and graphical displays.
• NEW! There is new treatment of the topic of loglinear smoothing.
• NEW! Treatment of Bayesian inference is now presented in parallel with frequentist methods.
• Introduction to the bootstrap method as a simple yet powerful tool that is integrated with general inferential procedures (Monte Carlo methods are also introduced.)
• Many exercises that enrich the book. (Some are relatively simple and reinforce calculations. Others concern bootstrap and Monte Carlo methods and theoretical material on survey sampling. Many incorporate use of the computer.)