Retherford R.D. Choe M.K. Statistical Models for Causal Analysis

NY: John Wiley & Sons, Inc., 1993. — 258 p. — ISBN: 0-471-55802-8.Simplifies the treatment of statistical inference focusing on how to specify and interpret models in the context of testing causal theories. Simple bivariate regression, multiple regression, multiple classification analysis, path analysis, logit regression, multinomial logit regression and survival models are among the subjects covered. Features an appendix of computer programs (for major statistical packages) that are used to generate illustrative examples contained in the chapters.Bivariate Linear Regression
Terminology
Fitting a Least-Squares Line
The Least-Squares Line as a Causal Model
The Bivariate Linear Regression Model as a Statistical Model
Statistical Inference: Generalizing from Sample
Goodness of Fit
Further Reading
Multiple Regression
The Problem of Bias in Bivariate Linear Regression
Multiple Regression with Two Predictor Variables
Multiple Regression with Three or More Predictor Variables
Dummy Variables to Represent Categorical Variables
Multicollinearity
Interaction
Nonlinearities
Goodness of Fit
Statistical Inference
Stepwise Regression
Illustrative Examples
Further Reading
Multiple Classification Analysis
The Basic MCA Table
The MCA Table in Deviation Form
MCA with Interactions
MCA with Additional Quantitative Control Variables
Expressing Results from Ordinary Multiple Regression in an MCA Format (all Variables Quantitative)
Presenting MCA Results Graphically
Further Reading
Path Analysis
Path Diagrams and Path Coefficients
Path Models with More Than One Exogenous Variable
Path Models with Control Variables
Saturated and Unsaturated Path Models
Path Analysis with Standardized Variables
Path Models with Interactions and Nonlinearities
Further Reading
Logіt Regression
The Linear Probability Model
The Logit Regression Model
Statistical Inference
Goodness of Fit
MCA Adapted to Logit Regression
Fitting the Logit Regression Model
Some Limitations of the Logit Regression Model
Further Reading
Multinomial Logit Regression
From Logit to Multinomial Logit
Multinomial Logit Models with Interactions and Nonlinearities
A More General Formulation of the Multinomial Logit Model
Reconceptualizing Contraceptive Method Choice as a Two-Step Process
Further Reading
Survival Models, Part 1: Life Tables
Actuarial Life Table
Product-Limit Life Table
The Life Table in Continuous Form
Further Reading
Survival Models, Part 2: Proportional Hazard Models
Basic Form of the Proportional Hazard Model
Calculation of Life Tables from the Proportional Hazard Model
Statistical Inference and Goodness of Fit
A Numerical Example
Multiple Classification Analysis (MCA) Adapted to Proportional Hazard Regression
Further Reading
Survival Models, Part 3: Hazard Models with Time Dependence
Time-Dependent Predictor Variables
Time-Dependent Coefficients
Further Reading
Арpendіx A. Sample Computer Programs
Description of the FIJIDATA File
SAS Mainframe Programs
Preparing Data for Survival Analysis
BMDP Mainframe Programs
LIMDEP Programs for IBM-Compatible Personal Computers
Appendix B. Statistical Reference Tables