Hoff, Peter D. (2009). A First Course in Bayesian Statistical Methods. London: Springer.
A functional and succinct introduction to basic concepts of Bayesian analysis, equipping the reader to conduct Bayesian versions of analyses including but not limited to multigroup comparisons, linear regression, generalized linear mixed effects models, and latent variable treatments of ordinal data. The author suggests that the intended audience includes non-statistics graduate students with basic graduate statistical training, although the technical details of the book will be challenging for many who match this description. The open-source statistical package R is used throughout the text to allow the reader to follow the examples and adapt the code for the reader’s own analyses.
[not available at Alkek]
Jackman, Simon (2009). Bayesian Analysis for the Social Sciences. UK: John Wiley & Sons.
Provides a reasonably self-contained introduction to Bayesian statistical inference with an emphasis on fundamentals in addition to focusing on social science applications. The topics covered are mainly for graduate level students and researchers looking to enhance their understanding of and uses for Markov Chain Monte Carlo (MCMC) methods using Bayesian statistical inference. Examples include exercises complemented by Win-BUGS/JAGS programs and R code. Appendices supply some mathematical and statistical background, covering vectors and matrices, the foundations of probability, some of the widely used probability mass functions and densities, and proofs of some key results concerning the conjugate analysis of normal data. The book is separated into three parts: (1) Introduction to Bayesian inference (2) Simulation methods, considering the two ‘MC’s of the Markov Chain Monte Carlo, and (3) Applications to the social sciences.
Lynch, Scott M. (2007). Introduction to Applied Bayesian Statistics and Estimation for Social Scientists.
New York: Springer.
Written to be a truly introductory book for social scientists on applied Bayesian analysis. This book is more accessible and assumes less prior reader knowledge than other Bayesian texts that are purported to be introductory. Analytic problems of realistic size for the social sciences are nevertheless addressed. After introducing probability theory and classical statistics, a variety of concepts relevant to modern Bayesian analyses are discussed in detail. Then, linear regression, generalized linear models, hierarchical linear models, and multivariate regression models are illustrated in the Bayesian framework. Programming for these applications is illustrated in the open-source statistical package R.
[not available at Alkek]
Categorical Data Analysis
Fleiss, Joseph L., Levin, Bruce, & Paik, Myunghee Cho. (2003). Statistical Methods for Rates and Proportions
(3rd ed.). Hoboken, New Jersey: John Wiley & Sons, Inc.
Organized in two levels of expertise with the higher level sections marked by asterisks. The first level covers methods with only as much complexity as necessary to give clear explanation and caters toward students with high school algebra background and the ability to take logarithms and exact square roots. The second level is meant for students of biostatistics and experts in data analysis and may require some familiarity with matrix algebra, multivariate statistical concepts, or asymptotic methods. This edition adds to the previous two new sections on logistic regression, Poisson regression, regression models for matched samples, the analysis of correlated binary data, and methods for analyzing fourfold tables with missing data. (Available at Texas State Library)
Hosmer, David W., & Lemeshow, Stanley. (2000). Applied Logistic Regression (2nd ed.). Hoboken, New Jersey:
John Wiley & Sons, Inc.
Covers the concepts of measures of model performance, diagnostic statistics, conditional analyses, and multinomial response data. The book recognizes the advancement of computer programs in statistics and aims to bridge the gap between the outstanding theoretical developments and the need to apply these methods to diverse fields of inquiry. Readers are assumed to have a solid foundation in linear regression methodology and contingency table analysis. Analyses in the book have been performed in STATA and also combine excellent graphics and analysis routines compatible across Macintosh, Windows and UNIX platforms. Other major statistical packages employed at various points include SAS, SPSS, and BMDP. (1st and 2nd edition available at Texas State Library)
McKnight, Patrick E., McKnight, Katherine M., Sidani, Souraya, & Figueredo, Aurelio Jose. (2007).
Missing Data: A Gentle Introduction. New York: The Guilford Press.
Presents a clear and comprehensive, non-mathematical discussion of missing data and distills information in current literature in order to give a broader perspective of missing data at a novice level. This book is meant for all scientists from students to experts with no assumptions of readers’ prior knowledge of the subject. It is a comprehensive reference for the detection, diagnosis, and treatment of missing data written in plain, nontechnical language. (Available at Texas State Library)
Kenny, David A, Kashy, Deborah A., & Cook, William L. (2006). Dyadic Data Analysis. New York: The Guilford Press.
This book thoroughly addresses the problem of the particular type of nonindependence that occurs in data with a dyadic structure. It assumes the reader is familiar with concepts such as correlation and regression, and has at least nominal familiarity with multilevel modeling, factor analysis, and structural equation modeling. Given this level of competence, a researcher will likely find in this book the information necessary to successfully execute most studies involving dyadic data. A variety of analyses relevant to the analysis of dyadic data are considered in detail, including but not limited to the actor-partner independence model, various social relations designs, one-with-many designs, and social network analysis. Detailed software examples are given throughout, usually in both SAS and SPSS.
[not available at Alkek]
Field, Andy (2009). Discovering Statistics Using SPSS (3rd Ed). London: Sage Publications.
Attempts to strike a good balance between theory and practice using SPSS. The author acknowledges the program’s ability to enable students to simply click away without fully understanding the theory behind the complicated calculations now made easy. Other books on SPSS describe how to compute data using the software but do so at the expense of theoretical concepts which this book adds. The book explains what different SPSS options do, what bits of the output mean, and if we ignore something, why we ignore it. The text allows the reader to use SPSS to tailor it toward their own specific needs rather than give step by step instruction as other SPSS books do. The book is meant for beginners with SPSS but can be used or referenced from first year undergraduate to professorship. Each chapter represents a different level of expertise and lays out information in a learning process that is fun and inventive. (Available at Texas State Library)
Kline, Rex B. (2004). Beyond Significance Testing: Reforming Data Analysis Methods in Behavioral Research.
Washington D.C.: American Psychological Association.
Intended for researchers and students in psychology and related areas without strong quantitative backgrounds but at least one undergraduate level course in behavioral science statistics. The goals of the book are to: (1) Review the short-comings in statistical testing (2) Discuss why such criticisms justify change in data-analysis practices (3) Help readers acquire new skills in effect size estimation and interval estimation for effect sizes (4) Review alternatives to statistical testing to include bootstrapping and Bayesian statistics. This book is suitable for an introductory course in behavioral science statistics at the graduate level and can also be used in a senior undergraduate level course that considers modern methods of data analysis. (Available at Texas State Library)
Lattin, James, Carrol, J. Douglas, & Green, Paul E. (2003). Analyzing Multivariate Data. CA: Brooks/Grove.
Covers major multivariate techniques for social science researchers. Oriented toward practical application of the techniques while also imparting a clear intuitive understanding of each technique by illustrating the idea geometrically. Written at a level roughly appropriate for first or second year graduate students in the social sciences. Has associated student workbooks oriented towards specific software packages (e.g., SPSS, SAS). Addresses major techniques in sequence. After the Overview section which introduces vectors, matrices, and regression, an Analysis on Interdependence section covers techniques including but not limited to exploratory and confirmatory factor analysis and multidimensional scaling. Then the Analysis of Dependence section covers techniques including but not limited to ANOVA, structural equation modeling, and logit choice models.
[not available at Alkek]
Stevens, James P. (2009). Applied Multivariate Statistics for the Social Sciences (5th Ed). New York: Taylor and
Written for those who use, rather than develop, advanced statistical methods and describes the material so the reader can understand the concepts instead of proving the results. The author includes numerous conceptual, numerical, and computer-related (SPSS, SAS) exercises in order to show the importance of checking data, assessing the assumptions, and adequate sample size so that results can be generalized. Two major additions to the book from previous editions are the chapters on Hierarchical Linear Modeling and Structural Equation Modeling. This book is intended for courses on multivariate statistics found in psychology, social science, education, and business departments but also appeals to practicing researchers with little or no training on multivariate methods. (Available at Texas State Library in hard copy and online)
Card, Noel A. (2012). Applied Meta-Analysis for Social Science Research.
New York: The Guilford Press.
A broad and deep treatment of meta-analysis that serves as both a pedagogical tool and a comprehensive reference. Little statistical knowledge is assumed, and the book includes guidance for the novice on conducting a first meta-analysis. Many cutting-edge developments are included. Examples are generally software-independent, although Mplus is used for certain illustrations.
Electronic version available via Alkek Library website:
Jaccard, James, & Jacoby, Jacob. (2010). Theory Construction and Model Building Skills.
New York: The Guilford Press.
Oriented toward teaching students and young professionals how to develop theories. Focuses less on philosophy of science and more on a variety of practical techniques for theory and model development. Includes applications to a variety of disciplines including but not limited to anthropology, economics, psychology, marketing, business, and education. Considers both qualitative and quantitative approaches, with more emphasis on quantitative. Chapters address topics including but not limited to the nature of understanding, creativity and idea generation, causal models, mathematical modeling, simulation as a theory development method, and reading and writing about theories.
Electronic version available via Alkek Library website:
Hox, Joop (2002). Multilevel Analysis: Techniques and Applications. NJ: Lawrence Erlbaum Associates.
Provides an introduction to Multilevel Analysis and is intended for applied researchers in the areas of psychology, education, sociology, and business. The author presents two multilevel models: the multilevel regression model and a model for multilevel covariance structures. In addition to an introduction to Multilevel Analysis, the book provides a discussion of many extensions and special applications for researchers who work in applied or theoretical research and to methodologists who consult with such researchers. The book utilizes non-technical terms for most of the discussions but assumes that readers already have a basic knowledge of social science statistics, including analysis of variance and multiple regression analysis.
Raudenbush, Stephen W. & Bryk, Anthony S. (2002). Hierarchical Linear Models (2nd Ed). California:
Recognizes the rapid growth of knowledge about hierarchical models. The book describes multilevel models, hierarchical linear models, and includes algorithms, programs, and provides examples in great detail based on the assumptions of linearity and normality. The book is meant mainly for social and behavioral scientists as well as a handbook or user manual for researchers of multilevel analysis. New chapters in this edition cover hierarchical generalized linear models, adding hierarchical models for latent variables, generalized multilevel nesting assumption, and a Bayesian perspective on hierarchical models with Markov Chain Monte Carlo computations. All correspond to the latest developments of the last decade in the field of multilevel analysis. (Available at Texas State Library)
Singer, Judith D. & Willett, John B. (2003). Applied Longitudinal Data Analysis: Modeling Change and Event
Occurrence. New York: Oxford University Press.
Uses concrete examples and careful explanation to demonstrate how research questions about change and event occurrence can be addressed with longitudinal data. Such questions on change include methods known as individual growth modeling, multilevel modeling, hierarchical linear modeling, random coefficient regression, and mixed modeling. Questions involving event occurrence include survival analysis, event history analysis, failure time analysis, and hazard modeling. Targeted readers are professional statisticians and their students who are comfortable with linear and logistic regression analysis as well as basic ideas of decent data analysis.
Crocker, Linda, & Algina, James. (1986). Introduction to Classical & Modern Test Theory.
Orlando, Florida: Harcourt Brace Jovanovich, Inc.
Written to help readers acquire the basic knowledge about classical psychometrics and how to integrate new ideas into that framework of knowledge. It does not contain “cookbook” steps on specific processes but instead uses technical discussion and statistical symbols to describe them. The text is meant for students who wish to acquire practice in reading material similar to that of a graduate textbook and professional literature. The material is organized into five units: Introduction to Management Theory, Reliability, Validity, Item Analysis in Test Development, and Test Scoring and Interpretation. Each discusses classical theoretical approaches as well as recent developments in each field.
De Ayala, R. J. (2009). The Theory and Practice of Item Response Theory. New York: The Guilford Press.
Describes and discusses Item Response Theory (IRT) which is used for equating alternate examination forms and is the foundation for many psychometric applications. The author addresses the “how to” of applying IRT models while at the same time providing enough technical substance to answer the “why” questions. References to appropriate outside sources are suggested for more technical reading while the exemplary model applications are expressed in the text using common software packages (BIGSTEPS, NOHARM, BILOG-MG, MULTILOG, PARSCALE). The terminology is more general than other IRT textbooks and the reader is assumed to be familiar with common psychometric concepts such as reliability, validity, scaling, levels of measurement, factor analysis, and regression analysis. (Available at Texas State Library)
Eye, Alexander V. & Mun, Eun Y. (2005). Analyzing Rater Agreement: Manifest Variable Methods.
NJ: Lawrence Erlbaum Associates Publishers.
Appeals to a broad range of students and researchers in the areas of psychology, biostatistics, medical research, education anthropology, sociology, and many other areas in which ratings are provided by multiple sources. The authors describe four approaches to the statistical analysis of rater agreement: (1) calculating coefficients to summarize agreement to a single rating (2) estimating log-linear models (3) exploring cross-classifications or raters’ agreement for indicators of agreement/disagreement (4) examining rater agreement by comparing the correlation or covariation structures of variables that raters use to describe objects, behaviors, or individuals. All of the methods discussed operate at the manifest variable level or at the level of observed variables. Included is a CD which contains additional exercises using the software presented in chapter five. (Available at Texas State Library)
Netemeyer, Richard G., Bearden, William O., & Sharma, Subhash (2003). Scaling Procedures: Issues and
Applications.CA: Sage Publications.
Focuses on developing and validating paper-and-pencil measures of latent social-psychological constructs. Mental/ability testing and classification measurement for clinical diagnosis are not an emphasis in the text but are used to describe the development and validation of social-psychological measures using classical theory and generalizability theory. The authors focus on constructs that can be assessed only indirectly as well as provide information about the issues involved in developing and validating multi-scales of self-report/paper-and-pencil measures. Chapter topics include dimensionality, reliability, validity, judging measurement items, designing/conducting studies to develop a scale, and finalizing a scale. (Available at Texas State Library)
Nunnally, Jum C. & Bernstein, Ira H. (1994). Psychometric Theory (3rd Ed). New York: McGraw-Hill Publishing.
Designed for researchers and for use in graduate courses in psychology, education, and areas of business such as management and marketing. The text describes the broad measurement problems that arise in these areas and includes several examples that allow hand calculation. General-purpose statistical packages are also included (SAS, LISREL, and Excel). This edition shows a shift away from classical procedures that explain variance to modern inferential procedures. A second major change from previous editions is the classification that has been given explicit status as a form of measurement distinct from scaling. Some procedures discussed may be deemed obsolete by researchers but may be necessary for some more novice individuals. (Available at Texas State Library
Raykov, Tenko, & Marcoulides, George A. (2010). Introduction to Psychometric Theory.
New York: Routledge, Taylor & Francis Group.
A fairly comprehensive, relatively non-technical introduction to psychometric theory, including item response theory. The framework of latent variable modeling is emphasized. A knowledge of introductory statistics including regression and ANOVA is recommended. The software packages R, SPSS, SAS, and especially Mplus are used to illustrate concepts using relevant datasets available from the book website PowerPoint lecture slides and other pedagogical materials are also available on this site.
[not available at Alkek]
Traub, Ross E. (1994). Reliability for the Social Sciences: Theory and Applications (Vol. 3).
CA: Sage Publications.
Written to address two issues not widely covered in previous publications of reliability theory: (1) accessibility of individuals not well-schooled in mathematics and statistics (2) degree of mathematical and statistical sophistication assumed of readers. This book does not utilize technical sophistication for describing reliability theory but instead provides a concise and relatively nontechnical introduction to the concepts and applications of basic reliability theory. The book is meant for social science students who will be using or referring to quantitative data in their research. The authors also stress the importance of these students to understand the error associated with the measurements and observations that produce quantitative data. (Available at Texas State Library)
Brown, Timothy A. (2006). Confirmatory Factor Analysis for Applied Research. New York: The Guilford Press.
Devoted to the topic of confirmatory factor analysis (CFA) and discusses the similarities /differences between exploratory factor analysis (EFA) and CFA, diagnosing and reflecting the various sources of the ill-fit of a measurement model, analysis of mean structures, modeling with multiple groups, CFA scale reliability evaluation, formative indicator models, and higher order factor analysis This book is not tied to any latent variable software packages but includes the five major programs (Amos, EQS, LISREL, Mplus, SAS/CALIS). The book is meant mainly for applied researchers and graduate students working within social and behavioral sciences (e.g., psychology, education, political science, management/marketing, sociology, public health). (Available at Texas State Library)
Byrne, Barbara M. (2012). Structural Equation Modeling With Mplus: Basic Concepts, Applications, and Programming.
New York: Routledge.
Provides readers a nonmathematical introduction to the basic concepts associated with Structural Equation Modeling (SEM), and illustrates it basic applications using the Mplus program. Addresses diverse SEM applications, including confirmatory factor analysis (CFA) and full latent variable models tested on a wide variety of data (single/multiple-group; normal/non-normal; complete/incomplete; continuous/ordinal), and based on either the analysis of covariance structures, or on the analysis of mean and covariance structures. All data files used in the book’s examples can be downloaded at the companion website (p. xi)
Electronic version available on Alkek Library website.
Kline, Rex B. (2005). Principles and Practice of Structural Equation Modeling (2nd ed.).
New York: The Guilford Press.
Intended as an accessible work about the principals and practice of structural equation modeling (SEM) for readers without extensive quantitative backgrounds. The fundamental concepts are presented in words and figures and not matrix algebra. Other works that better explain the mathematical foundations of SEM are cited throughout the book. One major area concerns the preparation and screening of data and basic principles of score reliability and validity (i.e., measurement theory). A review of basic statistical concepts, correlation, regression, and statistical tests are discussed as well as eight different SEM computer programs (AMOS, SAS/CALIS/STAT, EQS, LISREL, Mplus, Mx Graph, RAMONA/SYSTAT, and STATISTICA). (1st edition available at Texas State Library)
MacKinnon, David P. (2008). Introduction to Statistical Mediation Analysis.
New York: Lawrence Erlbaum Associates, Taylor & Francis Group.
Provides a comprehensive introduction to statistical, methodological, and conceptual aspects of mediation analysis. Substantive applications of mediation methods and applications in the development and evaluation of prevention and treatment programs are described for a wide variety of research areas (biology, sociology, epidemiology, social psychology, developmental psychology, and other areas). The book covers the single mediator model in detail before discussing extensions to advanced statistical methods including multilevel mediation models and longitudinal mediation models. The primary audiences for this book are advanced undergraduate students, graduate students, and researchers from substantive areas although persons without this exposure will still find the chapters very useful.
Pugesek, Bruce H., Tomer, Adrian, & Von Eye, Alexander (2003). Structural Equation Modeling:
Applications in Ecological and Evolutionary Biology. NY: Cambridge University Press.
Intended to help biologists understand the distinction between Structural Equation Modeling (SEM) and path analysis by discussing the basic formulation of the method as well as technical details on data analysis, interpretation, and reporting. The book is laid out in three sections: (1) Theory – describes the SEM model and practical matters of application (2) Applications – provides a sampling of the ways SEM is employed (3) Computing – discusses the three popular software packages that perform SEM analysis: Amos, EQS, and LISREL. (Available at Texas State Library)