Monographs of the Society for Research in Child Development最新文献

This first chapter introduces the main goals of the monograph and previews the remaining chapters. The goals of this monograph are to provide summaries of our current understanding of advanced developmental methodologies, provide information that can advance our understanding of human development, identify shortcomings in our understanding of developmental methodology, and serve as a flagpost for organizing developmental methodology as a subdiscipline within the broader field of developmental science. The remaining chapters in this monograph address issues in design (sampling and big data), longitudinal data analysis, and issues of replication and research accumulation. The final chapter describes the history of developmental methodology, considers how the previous chapters in this monograph fit within this subdiscipline, and offers recommendations for further advancement.

The overarching theme of this monograph is to encourage developmental researchers to acquire cutting-edge and innovative design and statistical methods so that we can improve the studies that we execute on the topic of change. Card, the editor of the monograph, challenges the reader to think about works such as the present one as contributing to the new subdiscipline of developmental methodology within the broader field of developmental science. This thought-provoking stance served as the stimulus for the present commentary, which is a collection of observations on "how we learn about methodology and statistics." The point is made that we often learn critical new information from our colleagues, from seminal writings in the literature, and from conferences and workshop participation. It is encouraged that researchers pursue all three of these pathways as ways to acquire innovative knowledge and techniques. Finally, the role of developmental science societies in supporting the dissemination and uptake of this type of knowledge is discussed.

The progression of scientific knowledge requires replication of research results and an orderly accumulation of research knowledge. However, developmental science, like many other sciences, has too often prioritized individual studies at the expense of replication and synthesis efforts. In this chapter, I describe the concepts of replication and research accumulation and consider both their barriers and potentials for developmental science. I emphasize the importance of considering effect sizes rather than statistical significance, and I describe meta-analysis as a powerful tool in facilitating research accumulation and in guiding replication efforts. By considering advancement in terms of research accumulation rather than single studies, developmental science can achieve greater efficiency and precision to guide both future research and applied efforts.

In this chapter, we demonstrate the way certain common analytic approaches (e.g., polynomial curve modeling, repeated measures ANOVA, latent curve, and other factor models) create individual difference measures based on a common underlying model. After showing that these approaches require only means and covariance (or correlation) matrices to estimate regression coefficients based on a hypothesized model, we describe how to recast these models based on time-series related approaches focusing on single subject time series approaches (e.g., vector autoregressive approaches and P-technique factor models). We show how these latter methods create parameters based on models that can vary from individual-to-individual. We demonstrate differences for the factor model using real data examples.

The study of change and variation within individuals, and the relative comparison of changes across individuals, relies on the assumption that observed measurements reflect true change in the construct being measured. Measurement properties that change over time, contexts, or people pose a fundamental threat to validity and lead to ambiguous conclusions about change and variation. We highlight such measurement issues from a within-person perspective and discuss the merits of measurement-intensive research designs for improving precision of both within-person and between-person analysis. In general, intensive measurement designs, potentially embedded within long-term longitudinal studies, provide developmental researchers an opportunity to more optimally capture within-person change and variation as well as provide a basis to understand changes in dynamic processes and determinants of these changes over time.

This chapter selectively reviews the evolution of quantitative practices in the field of developmental methodology. The chapter begins with an overview of the past in developmental methodology, discussing the implementation and dissemination of latent variable modeling and, in particular, longitudinal structural equation modeling. It then turns to the present state of developmental methodology, highlighting current methodological advances in the field. Additionally, this section summarizes ample quantitative resources, ranging from key quantitative methods journal articles to the various quantitative methods training programs and institutes. The chapter concludes with the future of developmental methodology and puts forth seven future innovations in the field. The innovations discussed span the topics of measurement, modeling, temporal design, and planned missing data designs. Lastly, the chapter closes with a brief overview of advanced modeling techniques such as continuous time models, state space models, and the application of Bayesian estimation in the field of developmental methodology.

Longitudinal data analytic techniques include a complex array of statistical techniques from repeated-measures analysis of variance, mixed-effects models, and time-series analysis, to longitudinal latent variable models (e.g., growth models, dynamic factor models) and mixture models (longitudinal latent profile analysis, growth mixture models). In this article, we focus our attention on the rationales of longitudinal research laid out by Baltes and Nesselroade (1979) and discuss the advancements in the analysis of longitudinal data since their landmark paper. We highlight the developments in growth and change analysis and its derivatives because these models best capture the rationales for conducting longitudinal research. We conclude with additional rationales of longitudinal research brought about by the development of new analytic techniques.