Intensive Longitudinal Analysis of Human Processes
Preview
Book Description
This book focuses on a span of statistical topics relevant to researchers who seek to conduct person-specific analysis of human data. Our purpose is to provide one consolidated resource that includes techniques from disciplines such as engineering, physics, statistics, and quantitative psychology and outlines their application to data often seen in human research. The book balances mathematical concepts with information needed for using these statistical approaches in applied settings, such as interpretative caveats and issues to consider when selecting an approach.
The statistical topics covered here include foundational material as well as state-of-the-art methods. These analytic approaches can be applied to a range of data types such as psychophysiological, self-report, and passively collected measures such as those obtained from smartphones. We provide examples using varied data sources including functional MRI (fMRI), daily diary, and ecological momentary assessment data.
Features:
- Description of time series, measurement, model building, and network methods for person-specific analysis
- Discussion of the statistical methods in the context of human research
- Empirical and simulated data examples used throughout the book
- R code for analyses and recorded lectures for each chapter available via a link available at https://personspecific.weebly.com/
Across various disciplines of human study, researchers are increasingly seeking to conduct person-specific analysis. This book provides comprehensive information, so no prior knowledge of these methods is required. We aim to reach active researchers who already have some understanding of basic statistical testing. Our book provides a comprehensive resource for those who are just beginning to learn about person-specific analysis as well as those who already conduct such analysis but seek to further deepen their knowledge and learn new tools.
Table of Contents
1. Introduction 1.1 First encounter with intra-individual variation. 1.2 Statistical Analysis of IAV: An overview of the structure of this book. 1.3 Description of exemplar data sets.1.4 Notation. 1.5 Conclusions. 2. Ergodic Theory: Mathematical theorems about the relation between IAV and IEV. 2.1 Introduction. 2.2 Some history regarding generalizability of IEV and IAV results. 2.3 Two conceptualizations of time series. 2.4 Some preliminaries. 2.5 Birkhoff’s theorem of ergodicity. 2.6 When is a system ergodic? 2.7 Heterogeneity as cause of non-ergodicity. 2.8 Example of a non-ergodic process. 2.9 Conclusions. 3. P-Technique. 3.1 The P-Technique Factor model. 3.2 The structural model of the covariance function of y(t) in P-technique factor analysis. 3.3 Conducting P-technique factor analysis. 3.4 Conclusions. 4. Vector Autoregression (VAR). 4.1 Brief introduction on the use of AR and VAR analysis in the study of human dynamics. 4.2 Elementary linear models for univariate stationary time. 4.3 Stability and stationarity. 4.4 Detrending data. 4.5 Univariate order selection. 4.6 General VAR model. 4.7 Multivariate order selection. 4.8 Testing of residuals. 4.9 Structural vector autoregression. 4.10 Granger causality. 4.11 Discussion. 5. Dynamic Factor Analysis. 5.1 General dynamic factor models. 5.2 Lag order selection. 5.3 Estimation. 5.4 Conclusions. 6. Model Specification and Selection Procedures. 6.1 Data-driven methods for person-specific discovery of relations among variables. 6.2 Filter methods. 6.3 Wrapper methods. 6.4 Embedded methods: Regularization. 6.5 Problems with individual-level searches. 6.6 Data aggregation approaches. 6.7 Group Iterative Multiple Model Estimation (GIMME) Approaches. 6.8 Conclusions. 7. Models of Intraindividual Variability with Time-Varying Parameters (TVPs). 7.1 The DFM(p,q,l,m,m) across N≥ individuals. 7.2 The DFM(p,q,l,m,m) with TVPs as a state-space model. 7.3 Nonlinear state-space model estimation methods. 7.4 Observability and controllability conditions in TVPs. 7.5 Possible functions for representing changes in the TVPs. 7.6 Illustrative examples. 7.7 Closing remarks. 8. Control Theory Optimization of Dynamic Processes. 8.1 Control theory optimization. 8.2 Illustrative simulation. 8.3 Summary. 9. The Intersection of Network Science and IAV. 9.1 Terminology. 9.2 Network measures. 9.3 Community detection algorithms. 9.4 Using community detection to subgroup individuals with similar dynamic processes. 9.5 Assessing robustness of community detection solutions. 9.6 Community detection and P-technique. 9.7 Discussion.
Author(s)
Biography
Kathleen (Katie) Gates is an associate professor of Quantitative Psychology in the Department of Psychology at the University of North Carolina at Chapel Hill. She obtained her Ph.D. in the Department of Human Development and Family Studies (quant focus) at Penn State, a Masters of Forensic Psychology at the City University of New York (John Jay College), and a BS in Psychology from Michigan State University. Katie’s work is motivated by problems in analyzing individual-level data. She develops algorithms and programs that may aid researchers in better quantifying behavioral, psychophysiological, and emotional processes across time. The end goal is to help researchers identify patterns within individuals so we can provide person-specific prevention, treatment, and intervention protocols as well as better understand the varied basic physiological underpinnings for emotions, cognition, and behaviors.
Sy-Miin Chow is Professor of Human Development and Family Studies at the Pennsylvania State University. She is an elected fellow of the Alexander von Humboldt Foundation in Germany and a winner of the Cattell Award from the Society for Multivariate Experimental Psychology as well as the Early Career Award from the Psychometric Society. Her work focuses on methodologies for handling intensive longitudinal data, methodological issues that arise in studies of change and human dynamics; and models and approaches for representing the dynamics of emotions, child development and family processes, as well as ways of promoting well-being and risk prevention.
Peter C. M. Molenaar is Distinguished Professor of Human Development and Family Studies at the Pennsylvania State University. He is a recipient of the Pauline Schmitt Russell Distinguished Research Career Award from the College of Health and Human Development at Penn State, the Aston Gottesman Lecture Award from the University of Virginia, the Sells Award for Distinguished Mulitvariate Research from the Society for Multivariate Experimental Psychology (SMEP), and the Tanaka Award from SMEP in 2017. His work instituted what many characterize as a conceptual and methodological paradigm-shift in the analysis of psychological, social, and behavioral processes from an inter-individual to an intra-individual variation perspective.