Confidence intervals in generalized regression models. With CD-ROM. Regression models are used to predict one variable from one or more other variables. Their goal is to create a model such that the predicted and observed values of the outcome variable are as similar as possible. This book presents well-known regression models (linear and non-linear models, binomial and logistic models, Poisson and multinomial models and other generalized regression models). The book follows two directions: profile likelihood-based confidence intervals and generalized regression models. It is intended for senior undergraduate and graduate students (generalized regression models) and for applied statisticians too (confidence intervals). Besides the textbook, a DVD with a restricted Mathematica version and the author’s own Statistical Inference Package (SIP) is also included. As the author explains, one of the aims of this book is to introduce a unified representation of different regression models, under the name generalized (parametric) regression models (GRM). Logically, the second aim of the book is to use a unified approach for statistical inference from statistical evidence consisting of data and its statistical models, under the name of likelihood-based approach. To conclude, the text and the corresponding software focus on producing statistical inference for data modeled by GRMs.

Keywords for this software

Anything in here will be replaced on browsers that support the canvas element