News Archive | The Methodology Center

News Archive

Bethany Bray, Ph.D.

January 26, 2015

As part of our annual series of one-credit courses in research methodology for Penn State graduate students, in fall 2015 we will offer, “Advanced topics in latent class analysis (LCA).” LCA is an analytic method used to identify hidden subgroups within a population based on individuals’ responses to multiple observed variables. This short course, taught by Methodology Center Investigator Bethany Bray, will build on the knowledge and skills presented in the short course, “An introduction to latent class and latent profile analysis.” Credit for that course is not a prerequisite for taking this course, but familiarity with LCA and baseline category multinomial logistic regression are prerequisites.


January 21, 2015

Michael ClevelandWe are pleased to announce this semester’s Taste of Methodology workshop on multilevel modeling (MLM) for analyzing clustered or longitudinal data. The May 5 workshop will be presented by Michael Cleveland, research assistant professor of health and human development and Methodology Center faculty affiliate.


MLMs are critical tools for analyzing clustered data, repeated measures data, and other forms of hierarchical data. These data could come, for example, from students who are nested within classrooms or participants who were followed for three or more observations.


A Taste of Methodology is a workshop series that offers Penn State faculty an overview of innovative methods over lunch. This semester’s workshop will present the concepts and applications of MLM in order to give faculty an efficient way to assess its potential for their research. 


January 16, 2015

If you work at Penn State, you should know that we hold monthly special interest group meetings open to all researchers and graduate students working with innovative research methods. The groups provide a forum for individuals to discuss their own research and to learn from others. This semester’s topics include analyzing complex data, mixture modeling, and causal analysis.


For dates, please see The Methodology Center’s calendar.


Linda Collins, Ph.D.January 12, 2015

Are you interested in the new approaches that are emerging for optimization of behavioral interventions? Linda Collins invites you to join a new special interest group on optimization of behavioral interventions that is being formed within the Society of Behavioral Medicine (SBM).  


This group will explore approaches to optimization of behavioral interventions, including, but not limited to, the multiphase optimization strategy (MOST); factorial and fractional factorial experiments; the sequential, multiple assignment, randomized trial (SMART); and system-identification procedures drawn from control engineering.

December 18, 2014

Runze LiCongratulations to Runze Li who was recently named the Verne M. Willaman Professor of Statistics at Penn State! Runze is an influential and productive researcher, a great mentor, a supportive and helpful colleague, and a delightful person. We are proud and honored to have him as part of our Center. His recent work has focused on time-varying effect models (TVEMs) and the analysis of high-dimensional data. His work on TVEM is helping answer new questions about relationships over time. His work on high-dimensional data is laying the groundwork for incorporating genetic data into behavioral research.

Read more about TVEM

Read more about high-dimensional data analysis

December 3, 2014

Rebecca Evans-PolceIn the United States, rates of substance use peak during adolescence and young adulthood. Previous literature has demonstrated that rates differ by race, ethnicity, and gender. Despite knowledge of these disparities, until now researchers have been unable to understand the extent to which these disparities change across adolescence and young adulthood. In the forthcoming article, “Changes in gender and racial/ethnic disparities in rates of cigarette use, regular heavy episodic drinking, and marijuana use: Ages 14 to 32,” to appear in Addictive Behaviors, Methodology Center researchers Rebecca Evans-Polce, Sara Vasilenko, and Stephanie Lanza use the time-varying effect model (TVEM) to examine the dynamic nature of substance use rates among different groups of adolescents and young adults.


December 1, 2014

Runze LiCongratulations to Runze Li for being named a Highly Cited Researcher by Thomson Reuters. This means that Runze is in the top one percent of most cited researchers in his field. Runze’s research focuses on the analysis of intensive longitudinal data (ILD) and high-dimensional data. During his 12 years as an investigator at The Methodology Center, Runze has been a pioneer not only in developing statistical methods but also in disseminating those methods to behavioral researchers. He led the development of the TVEM macro suite and the FHLM-LLR macro for analyzing ILD and PROC SCADLS & PROC SCADGLIM for selecting variables in high-dimensional data. Runze’s work is becoming even more relevant with the increasing availability of high-dimensional data, such as genetic data and ILD, such as data from smartphone studies. We look forward to many more years of collaborating with Runze.


Read about Runze’s research on analyzing ILD

November 10, 2014

Donna CoffmanPrevious literature has established that gang membership is associated with higher rates of drug use. In the forthcoming article, “Gang membership and substance use: Guilt as a gendered causal pathway,” in The Journal of Experimental Criminology, Methodology Center Investigator Donna Coffman and two other researchers examine whether anticipated guilt for substance use explains this association. The authors also expand the available set of methods for causal inference when assessing mediation in the presence of moderation and time-varying confounding.  

November 4, 2014

Susan MurphyIn our latest podcast, Amanda Applegate interviews Susan Murphy, Methodology Center principal investigator, Herbert E. Robbins Distinguished University Professor of Statistics, research professor at the Institute for Social Research, and professor of psychiatry at the University of Michigan. The discussion focuses two topics, the sequential, multiple assignment, randomized trial (SMART), which allows scientists to develop adaptive interventions, and the just-in-time, adaptive intervention (JITAI), which uses real-time data to deliver interventions as needed via mobile devices. Susan’s MacArthur Fellowship is also discussed; the podcast was recorded before she was elected to the Institute of Medicine of the National Academies.


November 3, 2014

output graphWe are pleased to release the latest version of the TVEM (time-varying effect model) SAS macro suite (v. 2.1.1). The macros in this suite estimate the coefficient functions in TVEMs for intensive longitudinal data (longitudinal data such as ecological momentary assessments, EMA, that are characterized by more frequent measurements than traditional panel data). 
Traditional analytic methods assume that covariates have constant effects on a time-varying outcome. The TVEM SAS macros allow the effects of covariates to vary with time. These macros enable researchers to answer new research questions about how relationships change over time. The newest version of the software includes some minor usability improvements.


Download the macro suite.

Not familiar with SAS macros? View our 4-minute video on how to run a macro.

Like Us On Facebook or Tweet This Page