Help Desk

Growth modeling within a multilevel modeling framework

In an earlier episode of Office Hours, Patrick addressed the question, “What is growth curve modeling?” In this episode he explores how a growth curve model can be estimated within the multilevel linear modeling (MLM) framework. Patrick begins by reviewing the assumption of independence in the general linear model and how this is violated when data are nested (e.g., children...

Coding time in growth models

Whether estimating growth models in a structural equation or multilevel modeling framework, the researcher must choose how to numerically code the passage of time. In this episode of Office Hours, Patrick explores the implications of scaling time within the general growth curve model. Patrick begins by revisiting the interpretation of the intercept of a regression line and then applies this...

Why use a Structural Equation Model?

In this edition of CBA Office Hours, Dan discusses some of the principal advantages of the structural equation model (SEM) relative to more traditional data analytic approaches like the linear regression model. Advantages include the ability to account for measurement error when estimating effects, test the fit of the model to the data, and specify statistical models that more closely align with...

The Many Uses of Network Analysis

The past two decades have given rise to significant advances in the development and application of methods for analyzing networks, particularly within the behavioral and health sciences. Network analysis considers how a set of units (or nodes) are connected to one another through directional or non-directional links (or edges). Analyzing the structure of a network involves the use of both...

What is Growth Curve Modeling?

As Patrick describes in the first of a series of videos, growth curve models can be useful whenever there is a focus on the analysis of change over time, such as when examining developmental changes, evaluating treatment effects, or analyzing diary data. Although growth models go by a variety of different names, all of these approaches share a common focus...

What’s the difference between finite mixture models and cluster analysis?

Researchers are often interested in identifying subgroups within their data to better understand heterogeneity within the population under study. This task has been the traditional domain of cluster analysis, but over the past decade or so finite mixture models have become an increasingly preferred alternative analytic technique. Sometimes referred to as "model-based clustering" the finite mixture model differs in important ways...

How many clusters do I need to fit a multilevel model?

In this edition of CBA Office Hours, Dan discusses a question that frequently comes up in our multilevel modeling workshop, namely, "How many clusters do I need to be able to fit a multilevel model?"  Here, clusters refers to upper-level units, so in the case of individuals nested within groups, the groups, and in the case of repeated measures, the individuals studied...

Syntax for Computing Random Effect Estimates in SPSS

Many programs can be used to fit multilevel models. For instance, in our multilevel modeling summer workshop, we demonstrate three programs: SAS, SPSS, and Stata. Unlike SAS, Stata, and many other programs, however, SPSS does not currently offer the option to output estimates of the random effects. Obtaining estimates of the random effects can be useful for a variety of...

The Human Desire to Categorize

Whether colors in the rainbow, notes in a musical scale, types of coffee, or country versus pop singers, there is a natural human desire to categorize objects and experiences. A story that recently appeared in the New York Times by Tom Vanderbilt presents a wonderful exploration of how we all find comfort in defining, seeking out, and confirming categories in...

Evaluating Interaction Effects

Often the most interesting research question is not whether a relationship between two variables exists but rather under what conditions the relationship holds. Put in statistical terms, we are often less interested in main effects than we are in interactions or moderation. An interaction implies that the magnitude of the relation between two variables differs as a function of some...

CenterStat's Help Desk is a blog in which Dan and Patrick respond to commonly asked questions about a variety of topics behavioral, educational, and health research including experimental design, measurement, data analysis, and interpretation of findings. The responses are intentionally brief and concise, and additional resources are provided such as recommended readings, provision of exemplar data and computer code, or links to other potential learning materials. Readers are welcome to submit their own questions for future Help Desk responses at [email protected].