Contents at a glance:

Models for categorical dependent variables:
Multinomial regression models
Ordinal regression models (PLUM)
Logit and probit models
Hierarchical loglinear models

Models for time-to-event (survival) data:
Actuarial life tables
Kaplan-Meier estimates
Cox regression, with and without time-dependent covariates

Regression models:
Nonlinear regression
Two-stage least squares
Weighted least squares

Additional procedures:
Linear mixed models
Generalized linear mixed models
ALSCAL
Variance-component estimation

Features:

• Clear and straightforward explanations of the statistical procedures and IBM SPSS Statistics output
• Detailed, integrated instructions for obtaining all the results shown
• Several examples for most procedures
• Datasets from various disciplines are analyzed and included on the accompanying CD
• Book reviewed by IBM staff

Examples include:

• Multinomial regression to predict degree of support for spending money on space exploration
• Ordinal regression models to examine ratings of the justice system
• Linear mixed models for testing hypotheses about achievement when students are clustered within schools
• Multidimensional scaling for examining perceived body-part structure
• Cox regression models for evaluating predictors of survival for patients with Hodgkin's disease

New to this edition: