Introduction to Linear Models and Statistical Inference (PDF)

A multidisciplinary approach that emphasizes learning by analyzing
real-world data sets

This book is the result of the authors' hands-on classroom
experience and is tailored to reflect how students best learn to
analyze linear relationships. The text begins with the introduction
of four simple examples of actual data sets. These examples are
developed and analyzed throughout the text, and more complicated
examples of data sets are introduced along the way. Taking a
multidisciplinary approach, the book traces the conclusion of the
analyses of data sets taken from geology, biology, economics,
psychology, education, sociology, and environmental science.

As students learn to analyze the data sets, they master
increasingly sophisticated linear modeling techniques,
including:

* Simple linear models

* Multivariate models

* Model building

* Analysis of variance (ANOVA)

* Analysis of covariance (ANCOVA)

* Logistic regression

* Total least squares

The basics of statistical analysis are developed and emphasized,
particularly in testing the assumptions and drawing inferences from
linear models. Exercises are included at the end of each chapter to
test students' skills before moving on to more advanced techniques
and models. These exercises are marked to indicate whether
calculus, linear algebra, or computer skills are needed.

Unlike other texts in the field, the mathematics underlying the
models is carefully explained and accessible to students who may
not have any background in calculus or linear algebra. Most
chapters include an optional final section on linear algebra for
students interested in developing a deeper understanding.

The many data sets that appear in the text are available on the
book's Web site. The MINITAB(r) software program is used to
illustrate many of the examples. For students unfamiliar with
MINITAB(r), an appendix introduces the key features needed to study
linear models.

With its multidisciplinary approach and use of real-world data sets
that bring the subject alive, this is an excellent introduction to
linear models for students in any of the natural or social
sciences.