Apply Now: Summer Institute on Just-in-Time Adaptive Interventions

Susan Murphy and Daniel AlmirallJanuary 23, 2020:

Apply now to attend this year’s Summer Institute on Innovative Methods, “Building effective just-in-time adaptive interventions using micro-randomized trial designs.” Susan Murphy, professor of statistics and computer science and Radcliffe Alumnae Professor at Harvard University, and Daniel Almirall, research associate professor at The University of Michigan’s Survey Research Center, will introduce the just-in-time adaptive intervention (JITAI) and micro-randomized trial (MRT) for the development of adaptive mobile health interventions. The Institute will be held July 23 – 24 in Bethesda Maryland.

JITAIs are a special type of adaptive intervention where—thanks to mobile technology like activity sensors and smartphones—an intervention can be delivered when and where it is needed. MRTs are a new trial design for addressing scientific questions concerning the construction of highly effective JITAIs. In this workshop, we will introduce JITAIs and provide examples of key scientific questions can be answered using MRTs. Useful primary aim data analysis methods for MRTs will also be discussed.

Day 1 and part of Day 2 of this workshop will focus on JITAI and MRT design considerations and applications. Much of Day 2 will be allotted to understanding primary aims in an MRT and conducting associated primary aim analyses.

The 2020 Summer Institute on Innovative Methods is hosted as a partnership between The Methodology Center at Penn State and the Center for Dissemination and Implementation Science at the University of Illinois at Chicago.

Read more or apply to attend.

Upcoming Webinar on Factorial Experiments

Linda M. Collins, Ph.D.January 14 2020:

In our next 1 & 1 webinar,  Methodology Center Director Linda M. Collins will present an introduction to factorial experiments. Our 1 & 1 webinars consist of a one-hour live video presentation on a method followed by a one-hour question-and-answer session with the presenter. The webinar will be held on Wednesday, February 5, 2020 from 3:00 to 5:00 p.m. Eastern Time.

Factorial experiments are sometimes used in research projects that follow the multiphase optimization strategy (MOST), an engineering-inspired framework for designing efficacious, effective, efficient, economical, and scalable behavioral and biobehavioral interventions. MOST relies heavily on efficient experimental design, and factorial experiments are often the most efficient design because they can provide the most statistical power with the fewest subjects (which may be counterintuitive to those who have been trained primarily in the randomized clinical trial). Factorial experiments with three or more factors, though not yet common in behavioral research, are a regular practice in the engineering design process. This webinar will be applicable for researchers from a broad array of disciplines.

To join, click when the webinar is starting. Registration in advance is not necessary, but participation will be limited to 500 people.

Letter from Linda Collins About The Methodology Center’s Future

December 3, 2019:

Hello everyone,

Linda M. CollinsSome substantial changes lie ahead for The Methodology Center, and I wanted to inform you about them personally. I am excited to announce that I have accepted a position as Professor of Social and Behavioral Sciences in the College of Global Public Health at New York University (NYU), starting in the fall of 2020. Due to this move and other changes, The Center’s Principal Investigators and I have decided not to request a renewal of our P50 Center grant from the National Institute on Drug Abuse. We have often mentioned that the P50 is and has been the cornerstone of Methodology Center funding for decades. As this grant winds down, The Methodology Center will continue to function normally — updating software, answering help desk emails, and updating the website — until next summer. Researchers then will focus on wrapping up the Center’s scientific projects. In actuality, though, the science will not be “wrapping up.” Each line of Methodology Center research will continue under the leadership of its Principal Investigator. So, though this is the end of an era at The Methodology Center, our scientists all will remain on the cutting edge of data analysis and experimental design research. More information about how to stay informed about our research will be described in the eNews next spring.

I came to Penn State in 1994 as professor of Health and Human Development and soon began directing The Methodology Center. Since that time, The Methodology Center has achieved and maintained its status as a National Institute on Drug Abuse P50 Center of Excellence, and Penn State has become an internationally recognized leader in methodology and prevention science. I would like to thank Penn State and the National Institutes of Health for their continuous support of our research, of which I am extremely proud.

I will always be grateful to Penn State for the collaborations and relationships I developed here, particularly those developed through the P50. I would especially like to thank the other P50 Principal Investigators: Stephanie Lanza, Runze Li, Bethany Bray (University of Illinois at Chicago) and Susan Murphy (Harvard University). Our stimulating, productive, and warm working relationship has endured for decades. I hope and trust we will collaborate on future projects.

Although leaving is undeniably hard, I am thrilled at the prospect of what the future will hold at NYU. My objective at NYU is to establish an intellectual hub for intervention optimization, in terms of both methodological advancement and innovative applications in health and education. There are literally hundreds of intervention scientists in the New York City area, so the possibilities are endless! My long-range goal is to establish intervention optimization as the norm by the year 2030.

Finally, I want to thank all of you who have taken the time to learn about and apply the methods we have worked on at The Methodology Center. I firmly believe that we can build a healthier society by improving experimental design and data analysis in the social, behavioral, and health sciences. In the coming months and years, I hope you will continue exploring the potential that methods have to enhance the impact of your research. Not sure where to begin? Try our website, and watch our newsletter for information about where our current website content will be migrating in 2020.

Best wishes,

Linda M. Collins

Video: Webinar on Configural Frequency Analysis

November 14, 2019:

Watch the video of our most recent webinar, “Person-Centered Methods: An Alternative Statistical Approach.” In this 90+ minute video, Mark Stemmler, professor of psychological assessment at the University of Erlangen-Nuremberg, Germany, and author of the book Person centered methods: Configural frequency analysis (CFA), introduces CFA. The webinar took place on October 31, 2019.

CFA is a data analysis method that can detect patterns that occur more or less often than would be expected to occur according to a prespecified null hypothesis. CFA is applicable across many fields, but in human development, researchers apply it to examine multiple behaviors and determine which patterns correlate to healthy or unhealthy development. This statistical tool can be applied to categorical variables, and continuous variables can be used as covariates.

Watch the video on YouTube.

Article: Does Collegiate Drinking Affect Graduate School?

Hannah Allen, Ph.D.October 10, 2019:

The high prevalence of heavy drinking among college students is widely known. Less clearly understood is how problematic alcohol use during college might be linked to post-college educational goals and attainment. In a recent article in the Journal of American College Health, Prevention and Methodology Training (PAMT) Postdoctoral Fellow Hannah Allen and a team of researchers from the University of Maryland examined the prospective relationship between alcohol abuse and dependence during college and graduate school plans and subsequent enrollment. They found that heavy drinking during college might impact graduate school enrollment and concluded that early intervention efforts could potentially help students achieve their educational goals.

The authors examined a sample of 980 students who participated in the College Life Study and graduated college within five years. Alcohol use was assessed throughout college, and participants indicated in their final year of college whether they had plans to attend graduate school. Enrollment in graduate school was assessed after college graduation, and all analyses controlled for demographic characteristics and college grade point average.

The authors found that college students meeting criteria for alcohol dependence were less likely to have plans to attend graduate school. Additionally, among those with plans to attend graduate school, both alcohol abuse and dependence during college were associated with decreased likelihood of actually following through on these plans and enrolling in graduate school after college. These findings support prior research studies that have found a negative association between problematic drinking in college and academic achievement.

Hannah, who performed the analyses in the study, explained the importance of studying graduate school enrollment as an academic outcome. “More and more young adults are choosing graduate school as a next step after college graduation. With an increasing number of career paths requiring a graduate degree, it is vital that we understand how substance use during college might interfere with students’ ability to meet their educational and career goals.”

Hannah continued, “Universities have a unique opportunity to intervene with students who are engaging in problematic alcohol use during college. Through a joint effort between academic advisors, career counselors, and campus health professionals, college students with graduate school aspirations should be made aware of the potential link between their current alcohol use and their health and success both during and after college graduation.”

Read the article. (Journal access required.)


Arria, A. M., Allen, H. K., Caldeira, K. M., Vincent, K. B., & O’Grady, K. E. (2019). Excessive drinking and drug use during college: Prospective associations with graduate school plans and attendance. Journal of American College Health, 1-7. doi: 10.1080/07448481.2018.1535494


Interest Group for Optimizing Interventions at SBM

Linda M. CollinsSeptember 27, 2019:
If you are interested in Linda M. Collins‘ research on the optimization of interventions and the multiphase optimization strategy (MOST), then you might be interested in the Society of Behavioral Medicine’s Optimization of Behavioral and Biobehavioral Interventions (OBBI) special interest group. The Society of Behavioral Medicine (SBM) is dedicated to to “providing new perspectives and progress on human behavior, health, and illness.” The OBBI special interest group provides opportunities for behavioral scientists and methodologists to network and discuss the optimization of behavioral and biobehavioral interventions. Questions? Contact OBBI Chair Sara St. George.

Lear more about SBM.

Article: Parental Monitoring and Adolescent Weight

September 16, 2019: John FeltDifferent researchers bring a diverse set of research backgrounds and interests to The Methodology Center. Prevention and Methodology Training (PAMT) Postdoctoral Fellow John Felt has applied his expertise in methods to a broad array of social and health problems. Recently, he worked with a team of researchers from California and Massachusetts to examine whether parental monitoring was related to obesity in adolescence. Their work was published in a recent issue of the journal, Obesity.

Adolescent obesity has been on the rise for decades in The United States. Higher levels of parental monitoring (that is, a parent’s level of awareness about where their children are and what they are doing) has been associated with many positive outcomes. In this study, the authors analyzed data from 4,773 participants of the Healthy Passages cohort study of emerging adolescents in Alabama, Texas, and California to understand the relationship between monitoring and health among adolescents.

The authors found that parental monitoring corresponded with a number of positive factors for adolescents. Regardless of race, higher parental monitoring was associated with higher consumption of healthy foods, lower consumption of unhealthy foods, and lower levels of screen time. Parental monitoring also correlated to lower weight overall. The research suggests that parenting-skills instruction could be a useful addition to youth-obesity interventions.

John performed the analysis on this project. His interest in measurement invariance has enabled him to research many important issues in public health, including racial and ethnic differences in health behaviors related to obesity, the experience of traumatic events, and quality of life. John explained why he thinks measurement invariance is important. “Measurement invariance is a latent variable method that allows us to test whether a given construct is interpreted similarly by different groups. If we do not establish measurement invariance in the groups we are comparing, we cannot rule out differences in measurement from actual meaningful group differences in what we are measuring.”


Read the article. (Journal access required.)



Kim, K. W., Wallander, J. L., Felt, J. M., Elliott, M. N., & Schuster, M. A. (2019). Associations of parental general monitoring with adolescent weight‐related behaviors and weight status. Obesity, 27(2), 280-287.

R Interest Group for Penn State

John DziakAugust 30, 2019:

This fall, Methodology Center Investigator and Programmer John Dziak will be hosting a special interest group for researchers who are interested in R software for statistical computing. The group is open to all, but it is geared toward teaching the basics of R to interested faculty and students.

This semester’s meetings will cover the basics of R. Pending interest, during spring semester the group will cover more advanced topics and take the form of a learning collaborative. Experience with R is not at all required, but it is recommended that people download R and R studio ( before attending. If you are interested in a specific R-related topic, please contact John directly. We hope to see you there!

R Special Interest Group
Dates: Wednesdays 9/18, 10/23, 11/13, and 12/04
1 – 2 p.m.
401 Health and Human Development Building
Contact: John Dziak (

Podcast: Getting Started in Grant Writing With Lisa Dierker

Lisa Dierker

August 28,2019:

In the current research landscape, researchers need to develop grant writing skills. In this podcast, Methodology Center Investigator and Professor of Psychology at Wesleyan University Lisa Dierker discusses topics including how to learn what works in grant writing, the best funding mechanisms, and how to approach grant writing as a methodologist or applied researcher. This podcast is intended for graduate students and junior investigators, but there are tips for more senior researchers as well.

Download Podcast 35

00:00 – Introductions
00:54 – Lisa’s background in research and grant writing
03:15 – The value of rejected grants
09:26 – Lisa’s favorite funding mechanisms
16:08 – How to get started in grant writing
19:45 – Whom to contact while preparing a grant
25:16 – How applied scientists can incorporate innovative methods into grant writing
28:48 – How methodologists can successfully get their work funded
31:15 – Pursuing grants in a difficult funding environment
34:15 – Top 3 pieces of advice on grant writing

Time-Varying Effect Modeling Interest Group for Penn State

Ashley Linden-CarmichaelAugust 5, 2019:

This fall, Methodology Center Investigator Ashley Linden-Carmichael will be hosting a special interest group for researchers who are interested in time-varying effect modeling (TVEM). TVEM is a data-analysis method that extends linear regression to allow the association between two variables to be modeled without making assumptions about the nature of the association.

The group will provide a forum for researchers to discuss their own research and to learn from others. Students, post-doctoral researchers and faculty are all invited.

Want to learn more about TVEM before the first meeting? Use the TVEM Learning Path to learn what questions TVEM can answer, how to prepare your data, how to run the macro, and more.

TVEM Special Interest Group
Dates: Tuesdays 9/24, 10/22, 11/19, and 12/10
noon – 1 p.m.
401 Health and Human Development Building
Contact: Ashley Linden-Carmichael (

To learn more, look for details about the TVEM course that Ashley will teach in spring semester of 2020.

Free Webinar on Configural Frequency Analysis

Mark Stemmler holding his bookJuly 10, 2019:

Configural frequency analysis (CFA) is a data analysis method that can detect patterns that occur more or less often than would be expected to occur according to a prespecified null hypothesis. CFA is applicable across many fields, but in human development, researchers apply it to examine multiple behaviors and determine which patterns correlate to healthy or unhealthy development. This statistical tool can be applied to categorical variables; in addition also continuous variables can be used as covariates.

Mark Stemmler, professor of psychological assessment at the University of Erlangen-Nuremberg, Germany, and author of the book Person centered methods: Configural frequency analysis (CFA), will be visiting The Methodology Center this fall. On Thursday, October 31, from 2:00 to 4:00 p.m. ET, Mark will present a 1 & 1 webinar on CFA. 1 & 1 webinars consist of a one-hour live video presentation on a method followed by a one-hour question-and-answer session with the presenter. CFA is easily performed through an R-package called confreq. The use of confreq will be demonstrated. To join the webinar, click when the webinar is starting. Registration in advance is not necessary.

Questions? Email:

Fond Farewells

Ben Bayly, Jessica Braymiller, Walter Dempsey, Cara Exten Rice, Jamie Gajos, Grace Mak, Sarah Perzow, Ashley Walton, Mengya XiaJuly 9, 2019:

Each academic year there are arrivals and departures, but 2019 has seen an unusually high number of former investigators and trainees moving up the ladder in their career. Join us in congratulating all of them!

  • Ben Bayly accepted a position as assistant professor of family studies, child and youth development in the agricultural economics, sociology, and education at Penn State.
  • Jessica Braymiller earned her Ph.D. (Double congrats!) and is now as a postdoctoral fellow at the University of Southern California.
  • Walter Dempsey, who recently completed his postdoctoral fellowship in biostatistics at Harvard University with Susan Murphy, accepted a position as assistant professor of biostatistics at University of Michigan.
  • Cara Exten Rice who has worked as research faculty in The Methodology Center, accepted a position as assistant professor of nursing at Penn State.
  • Jamie Gajos accepted a position as assistant professor of human development and family studies at University of Alabama.
  • Grace Mak earned her Ph.D. (Double congrats!) and is now postdoctoral scholar at the Dornsife Center for Self-Report Science at the University of Southern California.
  • Sarah Perzow, a former PAMT trainee, will graduate with her Ph.D. in clinical psychology in August and will begin a postdoctoral fellowship in psychology at The University of Denver.
  • Ashley Walton, who was also a postdoctoral fellow at Harvard with Susan, is now a research fellow in the cognitive science program at Dartmouth College.
  • Megya Xia earned her Ph.D. and accepted a position as assistant professor of psychology at the University of Alabama.

We look forward to the great science you will create in the future and to collaborating with each of you!

Building Better Adaptive Interventions by Expanding SMART

June 27, 2019:

John DziakBehavioral interventions for prevention and treatment are an important part of the fight against drug abuse and HIV/AIDS. Among the challenges faced by scientists is how and when to alter the course of treatment for participants in the intervention. Adaptive interventions change based on evidence about what is best for the participant at a given time.

For over a decade, Methodology Center researchers have developed and applied sequential, multiple assignment, randomized trials (SMARTs), which are experimental designs that can be used to build adaptive interventions that address a variety of health and behavioral challenges, such as substance abuse abstinence, weight loss, ADHD management, and language acquisition. Recently, researchers have begun developing methods to evaluate SMARTs by using multiple measures of the outcome over time rather than only considering the outcome at the end of the study. For example, a researcher who is developing an adaptive intervention to promote abstinence from alcohol may want to consider alcohol usage rates every month for six months to decide how to construct the intervention. In a recent article in Multivariate Behavioral Research by Methodology Center Investigator John Dziak, Methodology Center Affiliates Daniel Almirall and Inbal “Billie” Nahum-Shani, and others, the authors develop and demonstrate a new method for evaluating a SMART using repeated measures of a binary outcome (such as substance use versus nonuse).

The authors apply their method to the ENGAGE SMART study, which was conducted to help develop an adaptive intervention for promoting treatment engagement among cocaine- and alcohol-dependent individuals. The authors found that certain designs correlated to increased abstinence rates during the first two months but abstinence rates that were equivalent to other designs by the end of the study. Had the investigators measured relapse solely at six months, they would not have observed the relapse differences during the early months, which may have practical or clinical significance. The authors go on to provide guidelines for using multiple binary measurements of the outcome while analyzing data from a SMART.

Lead author John Dziak discussed the importance of the study. “SMART is a valuable method because conditions such as addiction and many other health problems, are chronic and often need treatment over time. In many cases, the appropriate treatment could change depending on the individual’s experiences. SMART trials can help scientists decide which set of adaptive treatment rules will work the best. In a lot of the past SMART literature, ‘work the best’ just meant having the best expected outcome at the end of the study.  But considering short-term and long-term effects together might help clinicians make better decisions to fit an individual’s  goals.  Also, it allows scientists to study delayed effects, where an early treatment choice affects how well later treatments work, and that could render theoretical insight into the treatments.”


Dziak, J. J., Yap, J. R., Almirall, D., McKay, J. R., Lynch, K. G., & Nahum-Shani, I. (2019). A data analysis method for using longitudinal binary outcome data from a SMART to compare adaptive interventions. Multivariate Behavioral Research, 1-24.

New Resource for Learning TVEM

simulated TVEM graphicMay 10, 2019:

Our newest resource helps scientists teach themselves how to use our time-varying effect modeling (TVEM) SAS macro. TVEM allows scientists to understand how associations between variables change over time. The TVEM Learning Path is designed to allow SAS users to efficiently teach themselves how to prepare data for, plan, and run a TVEM.

The Learning Path allows users to select from a variety of educational resources including videos, presentation slides, webpages, and hands-on SAS exercises. This format allows users to access the specific content they need in the format they desire to develop their skills as quickly as possible. Content is divided into

  • Conceptual introduction,
  • Detailed introduction,
  • Running a SAS macro,
  • Flipping data from long format to wide format,
  • Preparing to run a TVEM,
  • Running a TVEM,
  • Plotting results, and
  • Running the Weighted TVEM SAS macro.

We hope the Learning Path is useful and can be applied to other methods. Please send any thoughts, suggestions, or questions about the Learning Path to

Open the TVEM Learning Path.

New Study Aims to Prevent Spread of HIV in High-Risk Populations

photograph of a red ribbonMay 9, 2019:

Despite great strides in decreasing the HIV infection rate in the United States over the last three decades, certain populations remain at high risk of infection. Young men who have sex with men (YMSM), especially Black/African American and Hispanic/Latino YMSM who live in inner cities, account for the most new infections annually. A new paper in JMIR Research Protocols by researchers from Children’s Hospital Los Angeles, Methodology Center Investigators Bethany Bray and Cara Exten Rice, and graduate student Eric Layland, describes the protocol for a longitudinal research study designed to improve HIV care and prevention among Black/African American and Hispanic/Latino YMSM.

The goal of the Healthy Young Men’s Cohort Study is to prevent new HIV infections and improve engagement with HIV care among Black/African American and Hispanic/Latino YMSM. Investigators are collecting data on drug use, sexual risk and protective behaviors, health care connectedness, mental health, stress and discrimination, emotion regulation, personal history with trauma, and more. This mixed-methods study  combines qualitative data with quantitative and biological data in order to generate the richest and most accurate data possible. These data will help characterize Black/African American and Hispanic/Latino YMSM engagement in HIV care and prevention.

Methodology Center Investigator Bethany Bray spoke about why the Healthy Young Men’s Cohort Study will have a positive impact on the health of Black/African American and Hispanic/Latino YMSM in the future. “Research that can inform tailored approaches to prevention and treatment engagement is critical. Society cannot end the HIV epidemic by 2030 without focusing on the high-risk populations in these two cohorts. These data will serve as a resource to a broad range of researchers.”

In the Healthy Young Men’s Cohort Study, data will be collected eight times at six-month intervals. The study has retained 97% of participants over the first 12 months. We look forward to the insights this study will yield.


Kipke M. D., Kubicek K., Wong C. F., Robinson Y. A., Akinyemi I. C., Beyer W. J., Hawkins W., Rice C. E., Layland E., Bray B. C., & Belzer M. (2019). A focus on the HIV care continuum through the Healthy Young Men’s Cohort Study: Protocol for a mixed-methods study. JMIR Research Protocols 8(1). PMCID: PMC6365874

“MOST-ly Mingling” at SPR

May 1, 2019:

Kate GuastaferroMethodology Center Investigator Kate Guastaferro will host an informal gathering during the Society for Prevention Research 2019 Annual Meeting to socialize and network with people considering or applying the multiphase optimization strategy (MOST). The gathering will be held on Wednesday, May 29, at 7:00 p.m. at the Eclipse Kitchen & Bar in the Hyatt Regency San Francisco and is open to anyone who is interested. Kate will answer questions about MOST and facilitate connections between researchers with similar interests. We hope you can make it!