Search

Maximum Likelihood for Social Science

Strategies for Analysis
Michael D. Ward, John S. Ahlquist
Published online:

15 November 2018

Print publication:

15 November 2018
- Book
- - Get access
    
    Buy a print copy
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
This volume provides a practical introduction to the method of maximum likelihood as used in social science research. Ward and Ahlquist focus on applied computation in R and use real social science data from actual, published research. Unique among books at this level, it develops simulation-based tools for model evaluation and selection alongside statistical inference. The book covers standard models for categorical data as well as counts, duration data, and strategies for dealing with data missingness. By working through examples, math, and code, the authors build an understanding about the contexts in which maximum likelihood methods are useful and develop skills in translating mathematical statements into executable computer code. Readers will not only be taught to use likelihood-based tools and generate meaningful interpretations, but they will also acquire a solid foundation for continued study of more advanced statistical techniques.

5 - Model Evaluation and Selection
from Part II - Model Evaluation and Interpretation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 97-118
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Explains why model evaluation and selection must occur prior to inference and then develops the out-of-sample prediction heuristic for model evaluation.Specific attention paid to cross-validation.

12 - Strategies for Missing Data
from Part IV - Advanced Topics
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 249-270
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Discusses problems induced by missing data and the multiple imputation strategies for dealing with it.Introduces and compares EM and Gaussian copula imputation methods.

Preface
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp xvii-xxii
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

Part IV - Advanced Topics
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 217-218
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

6 - Inference and Interpretation
from Part II - Model Evaluation and Interpretation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 119-132
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Discusses the mechanics and computation for effectively interpreting theoutput of likelihood-based models in ways that are easy to understand and communicate.

Frontmatter
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp i-iv
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

Bibliography
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 277-292
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

3 - Maximum Likelihood for Binary Outcomes
from Part I - Concepts, Theory, and Implementation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 43-78
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Builds likelihood-based models for binary data and describes how we can evaluate the model and use sampling tools to generate meaningful interpretations of model quantities

Contents
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp v-x
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

8 - Ordered Categorical Variable Models
from Part III - The Generalized Linear Model
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 141-160
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Applies the GLM framework to modeling ordered categorical responses.Discusses the assumptions underlying the ordered logit/probit and provides diagnostics.Discusses categorical regressors.

4 - Implementing MLE
from Part I - Concepts, Theory, and Implementation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 79-94
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Provides some of the details of numerical optimization as applied to likelihood functions and discusses possible problems, both computational and data-generated.

1 - Introduction to Maximum Likelihood
from Part I - Concepts, Theory, and Implementation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 3-20
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

An overview of the basic concepts and components of likelihood-based modelling and introduces the process of maximizing a likelihood.We show that the OLS model can be derived in a likelihood framework.

Index
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 293-298
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

11 - Strategies for Temporal Dependence: Duration Models
from Part IV - Advanced Topics
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 219-248
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Introduces the notion of dependence across observations in the context of teporal duration models.Describes BTSCS, parametric, andthe Cox model. Introduces split population duration models.

9 - Models for Nominal Data
from Part III - The Generalized Linear Model
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 161-189
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Applies the GLM framework to modeling unorded categorical responses. Discusses the IIA assumption for the mutinomial logit and the many tools developed for times when it fails.

10 - Strategies for Analyzing Count Data
from Part III - The Generalized Linear Model
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 190-216
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation
Summary

Applies the GLM framework to modeling event count data. Discusses the common problem of overdispersion and the methods for extending the model to account for it.

Part II - Model Evaluation and Interpretation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 95-96
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

List of Tables
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp xv-xvi
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

Part I - Concepts, Theory, and Implementation
Michael D. Ward, Duke University, North Carolina, John S. Ahlquist, University of California, San Diego
Book:

Maximum Likelihood for Social Science

Published online:

15 November 2018

Print publication:

15 November 2018, pp 1-2
- Chapter
- - Get access
    
    Check if you have access via personal or institutional login
    
    Log in Register
- Export citation

Search Results

Refine search

Refine search

Actions for selected content:

37 results

Maximum Likelihood for Social Science

5 - Model Evaluation and Selection

Summary

12 - Strategies for Missing Data

Summary

Preface

Part IV - Advanced Topics

6 - Inference and Interpretation

Summary

Frontmatter

Bibliography

3 - Maximum Likelihood for Binary Outcomes

Summary

Contents

8 - Ordered Categorical Variable Models

Summary

4 - Implementing MLE

Summary

1 - Introduction to Maximum Likelihood

Summary

Index

11 - Strategies for Temporal Dependence: Duration Models

Summary

9 - Models for Nominal Data

Summary

10 - Strategies for Analyzing Count Data

Summary

Part II - Model Evaluation and Interpretation

List of Tables

Part I - Concepts, Theory, and Implementation

Search Results

Refine search

Refine search

Actions for selected content:

Save Search

37 results

Maximum Likelihood for Social Science

Summary

Summary

Summary

Summary

Summary

Summary

Summary

Summary

Summary

Summary