Logistic regression : from introductory to advanced concepts and applications

Index

Introduction : linear regression and logistic regression --
Log-linear analysis, logit analysis, and logistic regression --
Quantitative approaches to model fit and explained variation --
Prediction tables and qualitative approaches to explained variation --
Logistic regression coefficients --
Model specification, variable selection, and model building --
Logistic regression diagnostics and problems of inference --
Path analysis with logistic regression (PALR) --
Polytomous logistic regression for unordered categorical variables --
Ordinal logistic regression --
Clusters, contexts, and dependent data : logistic regression for clustered sample survey data --
Conditional logistic regression models for related samples --
Longitudinal panel analysis with logistic regression --
Logistic regression for historical and developmental change models : multilevel logistic regression and discrete time event history analysis --
Comparisons : logistic regression and alternative models.

In this text, author Scott Menard provides coverage of not only the basic logistic regression model but also advanced topics found in no other logistic regression text. The book keeps mathematical notation to a minimum, making it accessible to those with more limited statistics backgrounds, while including advanced topics of interest to more statistically sophisticated readers. Not dependent on any one software package, the book discusses limitations to existing software packages and ways to overcome them.

Key Features

Examines the logistic regression model in detail
Illustrates concepts with applied examples to help readers understand how concepts are translated into the logistic regression model
Helps readers make decisions about the criteria for evaluating logistic regression models through detailed coverage of how to assess overall models and individual predictors for categorical dependent variables
Offers unique coverage of path analysis with logistic regression that shows readers how to examine both direct and indirect effects using logistic regression analysis
Applies logistic regression analysis to longitudinal panel data, helping students understand the issues in measuring change with dichotomous, nominal, and ordinal dependent variables
Shows readers how multilevel change models with logistic regression are different from multilevel growth curve models for continuous interval or ratio-scaled dependent variables
Logistic Regression is intended for courses such as Regression and Correlation, Intermediate/Advanced Statistics, and Quantitative Methods taught in departments throughout the behavioral, health, mathematical, and social sciences, including applied mathematics/statistics, biostatistics, criminology/criminal justice, education, political science, public health/epidemiology, psychology, and sociology.