Analysis of Mixed Data: Methods & Applications, 1st Edition (Hardback) book cover

Analysis of Mixed Data

Methods & Applications, 1st Edition

Edited by Alexander R. de Leon, Keumhee Carrière Chough

Chapman and Hall/CRC

262 pages | 293 B/W Illus.

Purchasing Options:$ = USD
Hardback: 9781439884713
pub: 2013-01-16

FREE Standard Shipping!


A comprehensive source on mixed data analysis, Analysis of Mixed Data: Methods & Applications summarizes the fundamental developments in the field. Case studies are used extensively throughout the book to illustrate interesting applications from economics, medicine and health, marketing, and genetics.

  • Carefully edited for smooth readability and seamless transitions between chapters
  • All chapters follow a common structure, with an introduction and a concluding summary, and include illustrative examples from real-life case studies in developmental toxicology, economics, medicine and health, marketing, and genetics
  • An introductory chapter provides a "wide angle" introductory overview and comprehensive survey of mixed data analysis

Blending theory and methodology, this book illustrates concepts via data from different disciplines. Analysis of Mixed Data: Methods & Applications traces important developments, collates basic results, presents terminology and methodologies, and gives an overview of statistical research applications. It is a valuable resource to methodologically interested as well as subject matter-motivated researchers in many disciplines.


" . . . I think, this book should be a must for any scientist dealing with the problem of analyzing mixed data. And, I would also like to thank the editors, A. R. de Leon and K. C. Chough, for such a nice compilation of very interesting and recent works for us."

—Abhik Ghosh, International Society for Clinical Biostatistics

"…the book is well written. The editors have done a wonderful job of selecting the mix of topics to include in the volume, thereby providing the reader with the flavor of the diversity of areas where mixed data analysis is now standard practice. The technical level of the book will make it appealing to a wide audience—from methodologically oriented researchers, such as graduate students and researchers in statistics and biostatistics, to those interested in subject matter areas, such as medicine, genetics, and social sciences."

Journal of the American Statistical Association, June 2014

"This is a well-written book with broad coverage on various topics … Each chapter provides carefully selected examples and cases to show the application of presented methods and pointed out possible future research directions. This book has a wide coverage on recent methodological developments for mixed data analysis involving GLMM, copula models, Bayesian methods, and latent variable modeling as well as on the applications of mixed data analysis in various areas, including biology, epidemiology, econometrics, health policy, and social science. In summary, this is an outstanding research book for researchers interested in analysis of mixed data."

—Zhigang Li, Journal of Biopharmaceutical Statistics, 2014

"As far as I know, this is the first work in this area, which provides an excellent overview about statistical models, estimation, and applications. … The most impressive feature of the book is its broad scope; it covers most of the topics that are common for mixed data analysis. … This book includes cross-references between chapters with a combined index and uses unified notations, table formats, and terminologies across chapters. All these features enable readers to easily access the various topics of mixed data analysis. … this book is well written and well organized. It gives an excellent overview of mixed data analysis both in terms of methods and applications. In addition to the statistics area, this book would be a good reference for researchers and professionals from different areas such as developmental toxicology, economics, medicine and health, marketing, and genetics."

Biometrics, June 2014

Table of Contents

Analysis of mixed data: An overview

Alexander R. de Leon and Keumhee Carrière Chough


Early developments in mixed data analysis

Joint analysis of mixed outcomes

Highlights of book

Combining univariate and multivariate random forests for enhancing predictions of mixed outcomes

Abdessamad Dine, Denis Larocque, and François Bellavance


Predictions from univariate and multivariate random forests

Simulation study


Joint tests for mixed traits in genetic association studies

Minjung Kwak, Gang Zheng, and Colin O. Wu


Analysis of binary or quantitative traits

Joint analysis of mixed traits



Bias in factor score regression and a simple solution

Takahiro Hoshino and Peter M. Bentler



Bias due to estimated factor scores: Factor analysis model

Proposed estimation method

Simulation studies


Theoretical details


Joint modeling of mixed count and continuous longitudinal data

Jian Kang and Ying Yang


Complete data model

Handling missing data problem



Factorization and latent variable models for joint analysis of binary and continuous outcomes

Armando Teixeira–Pinto and Jaroslaw Harezlak


Clinical trial on bare-metal and drug-eluting stents

Separate analyses

Factorization models for binary and continuous outcomes

Latent variable models for binary and continuous outcomes



Regression models for analyzing clustered binary and continuous outcomes under the assumption of exchangeability

E. Olusegun George, Dale Bowman, and Qi An


Distribution theory and likelihood representation

Parametric models

Application to DEHP data

Litter-specific joint quantitative risk assessment


Random effects models for joint analysis of repeatedly measured discrete and continuous outcomes

Ralitza Gueorguieva



Estimation and inference



Hierarchical modeling of endpoints of different types with generalized linear mixed models

Christel Faes


Multivariate multi-level models

Special cases

Likelihood inference



Joint analysis of mixed discrete and continuous outcomes via copula models

Beilei Wu, Alexander R. de Leon, and Niroshan Withanage


Joint models via copulas


Likelihood estimation

Analysis of ethylene glycol toxicity data


Analysis of mixed outcomes in econometrics: Applications in health economics

David M. Zimmer


Random effects models

Copula models

Application to drug spending and health status

Application to nondrug spending and drug usage


Sparse Bayesian modeling of mixed econometric data using data augmentation

Helga Wagner and Regina Tüchler


Model specification

Logit-normal model

Modeling material deprivation and household income

Estimating consumer behavior from panel data


Bayesian methods for the analysis of mixed categorical and continuous (incomplete) data

Michael J. Daniels and Jeremy T. Gaskins



Characterizing dependence

(Informative) Priors

Incomplete responses

General computational issues

Analysis of examples


About the Editors

Alexander R. de Leon is Associate Professor in the Department of Mathematics and Statistics at the University of Calgary. Originally from the Philippines, he obtained his BSc and MSc, both in Statistics, from the School of Statistics of the University of the Philippines. After a research studentship at Tokyo University of Science, he completed his PhD in Statistics in 2002 at the University of Alberta. His research interests include methods for analyzing correlated data, multivariate models and distances for mixed discrete and continuous outcomes, pseudo- and composite likelihood methods, copula modeling, assessment of diagnostic tests, statistical quality control, and statistical problems in medicine, particularly in ophthalmology. Alex can be reached at

Keumhee Carriere Chough is Professor of Statistics in the Department of Mathematical and Statistical Sciences at the University of Alberta. After completing her BSc in Agriculture from Seoul National University, in Seoul, Korea, she earned her MSc from the University of Manitoba, and her PhD in Statistics from the University of Wisconsin-Madison in 1989. Since 1996, she has been with the Department of Mathematical and Statistical Sciences, University of Alberta, after stints as Assistant Professor at the University of Iowa (1990–1992) and University of Manitoba (1992–1996). She was also the Director of the Statistics Consulting Center at the University of Iowa (1990–1992). Her research interests include design and analysis for repeated measures data, missing data methods, high dimensional data analysis methods, multivariate methods, designs for clinical trials, item response data, variable selection methods, and survival analysis. As well, she specializes in such biostatistical methods as small area variation analysis techniques with applications to health care utilization. She has been a Health Scientist funded through the Alberta Heritage Foundation for Medical Research (1996–2011). She is a Fellow of the American Statistical Association, the Institute of Health Economics, and the Manitoba Centre for Health Policy. Keumhee can be reached at

Subject Categories

BISAC Subject Codes/Headings:
MATHEMATICS / Probability & Statistics / General