James P. Selig

Advantages of Monte Carlo Confidence Intervals for Indirect Effects

Monte Carlo simulation is a useful but underutilized method of constructing confidence intervals for indirect effects in mediation analysis. The Monte Carlo confidence interval method has several distinct advantages over rival methods. Its performance is comparable to other widely accepted methods of interval construction, it can be used when only summary data are available, it can be used in situations where rival methods (e.g., bootstrapping and distribution of the product methods) are difficult or impossible, and it is not as computer-intensive as some other methods. In this study we discuss Monte Carlo confidence intervals for indirect effects, report the results of a simulation study comparing their performance to that of competing methods, demonstrate the method in applied examples, and discuss several software options for implementation in applied settings.

Mediation Models for Longitudinal Data in Developmental Research

Mediation models are used to describe the mechanism(s) by which one variable influences another. These models can be useful in developmental research to explicate the relationship between variables, developmental processes, or combinations of variables and processes. In this article we describe aspects of mediation effects specific to developmental research. We focus on three central issues in longitudinal mediation models: the theory of change for variables in the model, the role of time in the model, and the types of indirect effects in the model. We use these themes as we describe three different models for examining mediation in longitudinal data.

New developments in latent variable panel analyses of longitudinal data

We review fundamental issues in one traditional structural equation modeling (SEM) approach to analyzing longitudinal data — cross-lagged panel designs. We then discuss a number of new developments in SEM that are applicable to analyzing panel designs. These issues include setting appropriate scales for latent variables, specifying an appropriate null model, evaluating factorial invariance in an appropriate manner, and examining both direct and indirect (mediated), effects in ways better suited for panel designs. We supplement each topic with discussion intended to enhance conceptual and statistical understanding.

Confirmatory Factor Analysis of a Family Quality of Life Scale for Families of Kindergarten Children Without Disabilities

Recently, within the field of special education, attention has been accorded to the conceptualization and measurement of family outcomes. The Family Quality of Life (FQOL) Scale is an instrument that can be used to measure family outcomes for families who have children with disabilities, and it has been demonstrated to have psychometric validity. To expand the usability of the FQOL Scale, the authors tested its measurement properties for families of kindergarten children without disabilities. Results from this new population of interest indicated adequate fit of the sample data to the theoretical model. Policy and program implications are discussed.

Modeling Time-Dependent Association in Longitudinal Data: A Lag as Moderator Approach

We describe a straightforward, yet novel, approach to examine time-dependent association between variables. The approach relies on a measurement-lag research design in conjunction with statistical interaction models. We base arguments in favor of this approach on the potential for better understanding the associations between variables by describing how the association changes with time. We introduce a number of different functional forms for describing these lag-moderated associations, each with a different substantive meaning. Finally, we use empirical data to demonstrate methods for exploring functional forms and model fitting based on this approach.

A Typological Approach to the Study of Parenting: Associations between Maternal Parenting Patterns and Child Behaviour and Social Reception.

The present work addresses the associations between self‐reported maternal parenting behaviours and aggression, personality and peer regard of children (n = 119) in early childhood (ages three–six years). A k‐means cluster analysis derived types of mothers based on their relative use of autonomy support and restrictive control. Outcomes included mother and teacher reports of physical and relational aggression, personality and peer acceptance as well as a peer nominations procedure for social reception. As hypothesised, children of mothers who report demonstrating little autonomy support and high restrictive control were more aggressive, less agreeable, conscientious, extraverted, and less well accepted by their peers. Findings are discussed in terms of maternal attributions of maternal behaviour, child behaviour in multiple contexts, and differential perceptions of mothers and teachers.

Evaluating Special Educator Effectiveness: Addressing Issues Inherent to Value-Added Modeling.

States are increasingly using value-added approaches to evaluate teacher effectiveness. There is much debate regarding whether these methods should be employed and, if employed, what role such methods should play in comprehensive teacher evaluation systems. In this article, we consider the use of value-added modeling (VAM) to evaluate special educators. We examine the potential difficulties that may be due to individualized needs and characteristics of students with disabilities, the context within which special education services are delivered, and aspects of VAM that have a differential impact on the value-added scores of special education teachers.

The Combined Effects of Grade Retention and Targeted Small-Group Intervention on Students' Literacy Outcomes

This study matched 15 kindergarten and 1st-grade retained students in 7 schools with their promoted peers on grade-level literacy performance. Researchers collected literacy assessments, demographic information, and instruction dosage data. Retained kindergarten students received less intervention and did not benefit academically from retention. Promoted 1st-grade students who received additional small-group interventions showed a nearly significant interaction effect. Results suggest that approximately 2.5 hr per school day of general education and small-group intervention literacy instruction is needed to bring students within average range. The article discusses instructional and policy implications.

Multilevel Modeling for Research in Group Work

Researchers in group counseling often encounter complex data from individual clients who are members of a group. Clients in the same group may be more similar than clients from different groups and this can lead to violations of statistical assumptions. The complexity of the data also means that predictors and outcomes can be measured at both the client and the group level. Researcher questions may focus on variables at the client level or the group level, or the interaction of client and group level variables. In this article, we introduce multilevel modeling as a tool that can be used both to account for the complex structure of the data and to incorporate variables at both the client and group levels. A published group counseling study is used as an example.

Ignoring individual differences in times of assessment in growth curve modeling

Researchers often collect longitudinal data to model change over time in a phenomenon of interest. Inevitably, there will be some variation across individuals in specific time intervals between assessments. In this simulation study of growth curve modeling, we investigate how ignoring individual differences in time points when modeling change over time relates to convergence and admissibility of solutions, bias in estimates of parameters, efficiency, power to detect change over time, and Type I error rate. We manipulated magnitude of the individual differences in assessment times, distribution of assessment times, magnitude of change over time, number of time points, and sample size. In contrast to the correct analysis, ignoring individual differences in time points frequently led to inadmissible solutions, especially with few time points and small samples, regardless of the specific magnitude of individual differences that were ignored. Mean intercept and slope were generally estimated without bias. Ignoring individual differences in time points sometimes yielded overestimated intercept and slope variances and underestimated intercept–slope covariance and residual variance. Parameter efficiency as well as power and Type I error rates for the linear slope were unaffected by the type of analysis.