Video: Webinar on Multilevel Modeling

January 09, 2019:

This is a video of the webinar on multilevel modeling (MLM) for intensive longitudinal data that Methodology Center Investigator Michael Russell presented on November 14, 2018. The video includes both the presentation and the question-and-answer session that followed. Portions of the video were re-recorded due to audio problems with recording of the original webinar. The video is a great way to get started with MLM for intensive longitudinal data.
MLM is an extension of linear regression that adjusts for the statistical dependence that occurs when multiple observations are collected from each individual. It also allows the separation of within- and between-person associations. MLM is a powerful and flexible approach that allows users to specify a wide range of models and address diverse research questions using ILD. .

Watch our website and eNews for information about upcoming 1 & 1 webinars.

Watch the video on YouTube.

Coffee Hour for Research Faculty

December 12, 2018:

In an effort to expand collaborations and community among the research faculty in the College of Health and Human Development, The Methodology Center will be hosting a casual coffee hour one Friday morning each month. This monthly get together is meant to create a zero-pressure environment for socializing and networking. Research faculty across the college are invited to attend. We will gather on the following mornings during the spring semester.

All coffee hours will be in 401 HHD Building, 8:30 – 9:30 a.m., Friday mornings.

January 11
February 8
March 15,
April 12
May 10

We hope you will join us!

Applications Open for May 2019 Training on Optimization

December 1, 2018:Linda M. Collins

Apply now to attend the Training on Optimization of Behavioral and Biobehavioral Interventions in Bethesda, Maryland on May 13-17, 2019. The goal of this five-day training is to help attendees gain the skills they need to use the multiphase optimization strategy (MOST) to optimize behavioral and biobehavioral interventions. This training is designed for those at any career level who have a terminal degree and who are planning to pursue, or have pursued, funding to conduct research involving MOST.

Methodology Center Investigators Linda Collins and Kate Guastaferro will serve as instructors.  Angela Pfammatter and Heather Wasser, alumni of MOST training who have applied experience with MOST, will serve as associate instructors.

Topics to be covered 

  • multiphase optimization strategy (MOST): preparation, optimization, and evaluation
  • development of a conceptual model
  • design of optimization trials, with an emphasis on factorial designs
  • power for optimization trials
  • selection of the components that will comprise the optimized intervention, based on optimization trial results
  • analysis of data from an optimization trial using either SAS or R
  • practical aspects of conducting optimization trials in varied field settings
  • obtaining funding for optimization projects

Applications are closed

Featured Article: Counting Drinks to Understand Alcohol Use Disorder

November 27, 2018:
ALC - square

Alcohol use disorder (AUD) occurs more frequently among young adults than other age groups. Heavy drinking, which is a strong predictor of whether someone will experience an AUD, is common among young adults. The generally accepted guideline for “heavy episodic drinking” or a “binge” is four (for women) or five (for men) or more drinks during a drinking occasion or within a two-hour period. In a forthcoming article by Methodology Center researchers Ashley Linden-Carmichael, Michael Russell, and Stephanie Lanza, the authors used time-varying effect modeling (TVEM) to examine whether these drink thresholds provide the best picture of who is at risk for AUD.

The authors analyzed a sample of more than 6,000 young adult drinkers from the National Epidemiologic Survey on Alcohol and Related Conditions-III. Among other questions, the authors examined whether consuming different average numbers of drinks on each drinking occasion was associated with higher prevalence of AUD. They found that rates of AUD for women increased until women reached about nine drinks per drinking session, when AUD rates plateaued at about 80%. AUD rates plateaued at 80% for men when they consumed about 12 drinks. This study suggests that defining a binge as four or five drinks and focusing prevention messages around that threshold neither matches young adult behavior nor does it enable us to understand the full scope of risky drinking.

Lead author Ashley Linden-Carmichael spoke about the implications of the findings and what further questions remain. “Alcohol clinical trials often use percentage of no-binge-drinking days as a marker of the trial’s efficacy. Our results suggest that focusing on reducing the number of drinks rather than whether they surpassed a threshold may be a better measure of treatment success.” Realistic and useful standards for what constitutes risky drinking could serve as an important tool in the effort to curb young-adult drinking to safer levels.

For a pre-print copy of the article, please email mcHelpDesk@spu.edu.

 

Reference

Linden-Carmichael, A. N., Russell, M. A., & Lanza S. T. (In press). Flexibly modeling alcohol use disorder risk: How many drinks should we count? Psychology of Addictive Behaviors.

Using REDCap to Manage Data With MOST

November 26, 2018:
red baseball cap

When following the multiphase optimization strategy (MOST) to build an intervention, it is often most efficient to conduct an optimization trial using an experimental design that requires management of many more conditions than would be necessary in the typical two- or three-arm randomized controlled trial (RCT). Examples are traditional factorial experiments and sequential, multiple assignment, randomized trials (SMARTs). Running an experiment with numerous conditions can be daunting to researchers who are accustomed to RCTs. To facilitate the smooth management of data from a variety of types of optimization trials, we asked Chuck Cleland at New York University to develop the guide to Research Electronic Data Capture (REDCap) for MOST.

REDCap is a secure web application for building and managing online surveys and databases. REDCap’s user-friendly web-based interface makes it an excellent tool for data management. Chuck Cleland’s excellent guide will help you use REDCap to manage complex optimization trials efficiently. The website includes text description, REDCap’s videos, and an example factorial experiment with screenshots. This resource will help interested scientists to organize, run, and track their experiments in the optimization phase of MOST.

Open the guide.

Video: Webinar on Postdoctoral Fellowships

November 13, 2018:

Thanks to all who participated in our informational webinar on postdoctoral fellowships in the Prevention and Methodology Training (PAMT) program. This is a video of the webinar that Bethany Bray, associate training director of PAMT, presented on Tuesday, November 6, 2018. The video includes both the presentation and the question-and-answer session that followed. The video is an excellent introduction for anyone who is considering applying for a PAMT fellowship. We recommend that interested graduate students watch this video and follow up with any remaining questions.

PAMT produces scientists who are trained in the integration of prevention science and statistical methodology, and it offers a unique opportunity for postdoctoral researchers to continue their training under the mentorship of established researchers in both The Bennett Pierce Prevention Research Center and The Methodology Center in Penn State’s College of Health and Human Development. PAMT is funded by the National Institute on Drug Abuse through a T32 grant to enable participants to develop their own line of research.

Watch our website and eNews for information about upcoming webinars.

Watch the video on YouTube.

Linda Collins to Give Schmitt Russell Research Lecture

October 31, 2018:lmc

Methodology Center Director Linda M. Collins will present the talk, “Bringing Health and Education Interventions into the 21st Century,” for the 2018 Schmitt Russell Research Lecture. The talk is open to the public and will be given at 4:00 p.m. on Wednesday, November 7, in the Bennett Pierce Living Center on Penn State’s University Park campus. The lecture is part of the Pauline Schmitt Russell Distinguished Career Award from Penn State’s College of Health and Human Development, which Linda was awarded in 2017.

Linda’s research focuses on experimental and non-experimental design, particularly for building, optimizing, and evaluating health and education interventions. In this talk, Linda will explore how the methods that scientists use for intervention design can be improved by implementing concepts borrowed from the engineering design process.

Linda and her collaborators have been developing these ideas in the mutliphase optimization strategy (MOST) for optimizing interventions over the last 15 years. In 2018, Linda authored one book and edited another about MOST in order to make these ideas more broadly available, clear, and applicable.

Read more about MOST.

Featured Article: LCA on Trends in Teen Marijuana Use

October 17, 2018:jlb

Over the last several years, laws about marijuana use have been changing across the United States. Methodology Center researchers Jessica Braymiller, Ashley Linden-Carmichael, and Stephanie Lanza wanted to know how marijuana use and attitudes about marijuana use might be changing in the face of those legal changes. In a recent article in Journal of Adolescent Health, the authors examined these questions using data from the 2010-2016 waves of the Monitoring the Future study.

The authors applied latent class analysis (LCA) to reveal patterns in marijuana use and attitudes among high school seniors in the United States. The analysis revealed that beginning in 2014, increases were observed in two subgroups: nonusers who are tolerant of marijuana use and marijuana users who generally approve of marijuana use at any level (i.e., experimentation, occasional use, and regular use).

Jessica Braymiller, graduate student at The Methodology Center and lead author on this paper, explained the implications of these findings. “Our findings indicate that many high school seniors in the United States have used marijuana recently and/or have approving attitudes regarding marijuana use at any frequency. Interestingly, the prevalence of these subgroups have increased in recent years, and males are most likely to belong to these subgroups. Since many adolescents are tolerant of marijuana use by the time they reach 12th grade, prevention and intervention efforts should address marijuana use behaviors and related attitudes early on.”

She went on to describe the value of applying latent class models to mature panel data like Monitoring the Future. “LCA allows researchers to categorize and describe individuals based on variety of shared characteristics. This approach is particularly useful in the context of nationally representative data sets, as we are able to comprehensively examine patterns of multiple behaviors and attitudes within a given population. Further comparing these patterns based on demographic characteristics enables researchers to identify population subgroups who may be at risk, having important implications for prevention and intervention efforts.”

Open the article.

Reference

Braymiller, J. L., Masters, L. D., Linden-Carmichael, A. N., & Lanza S. T. (2018) Contemporary patterns of marijuana use and attitudes among high school seniors: 2010–2016. Journal of Adolescent Health, 63(4), 394-400.

Podcast: Social Network Analysis With Ashton Verdery

October 10, 2018:AV
In our latest podcast, Ashton Verdery, assistant professor of sociology and demography at Penn State, discusses social network analysis (SNA). One increasingly important use of SNA is to study marginalized populations who are otherwise hard to sample. In health, behavioral, and social sciences, SNA has been used to examine how people relate to one another; how relationships affect the flow of items such as diseases, goods, information, or behaviors; how individual positions in broader network structures affect the risks of contracting diseases, hearing of opportunities, or generating new ideas; and more. In this podcast, Ashton explains the value and challenges of SNA in a behavioral health context. He also discusses projects from his research, including his work studying the heroin crisis in Pennsylvania, kidney transplant candidates, and migrant populations.

Download podcast 34.


Timeline

00:00 – Introduction
00:31 – What is social network analysis (SNA) and why do it?
03:51 – Why does SNA interest you?
05:46 – Why is SNA valuable in behavioral health?
09:00 – Do policy changes affect migrants’ social networks?
13:15 – What are the methodological challenges in SNA?
19:17 – How are the social network questions different and similar in your research projects on kidney transplants and your research on the heroin crisis?

Penn State Launches New Consortium to Combat Opioid Crisis

October 3, 2018:stl

Pennsylvania is one of the states most impacted by the growing opioid epidemic, with one of the highest overdose death rates in the country — but a new initiative bringing together experts from across Penn State aims to combat this crisis through data-driven, evidence-based innovation.

The Penn State Consortium to Combat Substance Abuse (CCSA) will draw on the expertise of researchers, educators and practitioners from across Penn State. The group plans to develop and implement effective programs, policies and practices aimed at preventing and treating addiction and its spillover effects on children, families and communities.

The CCSA will be led by interim director Stephanie Lanza, professor of biobehavioral health, Methodology Center principal investigator, and director of The Edna Bennett Pierce Prevention Research Center at Penn State.

“Pennsylvania and the nation need more research into this troubling epidemic,” Stephanie said. “I believe that the Penn State community can create lasting impacts through educating one another, our students and the public, and by undertaking research that advances evidence-based programs, policies and practices to better understand, prevent and treat opioid and other substance misuse and addiction.”

The CCSA will be housed in Penn State’s Social Science Research Institute, one of seven cross-University research institutes within the Office of the Vice President for Research. One of the consortium’s signature efforts will be the strategic hiring of 12 new tenure-track faculty members over the next four years, who will bring additional expertise in this critical field to the University and lead the charge to research and develop data-driven solutions to this public-health crisis.

“Across the University, individuals have been working in their labs, communities and elsewhere to identify this epidemic’s causes, pursue solutions and address systemic substance-abuse issues,” said Penn State Executive Vice President and Provost Nick Jones. “As Pennsylvania’s only land-grant institution, Penn State has a vital responsibility to lead the way in fighting this battle. By forging connections across our colleges and campuses and working with community leaders, we can tackle this epidemic head-on and work toward a world free from the disease of opioid addiction.”

The CCSA will provide seed-grant funding for new interdisciplinary teams aimed at combating opioid and other substance abuse and sponsor an annual conference to bring together substance abuse prevention experts from across the nation.

“The faculty within the Penn State Consortium to Combat Substance Abuse will join with our current faculty to conduct innovative, interdisciplinary and translational research to illuminate risk factors for substance use, abuse and addiction; to educate their students and the public; and apply their knowledge to prevent and treat addiction,” said Penn State Vice President for Research Neil Sharkey.

A national search for a permanent consortium director will be launched this fall.

MOST Teachers’ Corner: New Resource for Teaching and Learning

October 2, 2018:most: new resource

The MOST Teachers’ Corner provides resources for instructors who want to incorporate instruction on the multiphase optimization strategy (MOST) into methods courses. The download will enable instructors to easily prepare a presentation that introduces MOST during one class session. The MOST Teachers’ Corner includes a PowerPoint presentation and recommended readings. Linda Collins crafted the PowerPoint using her extensive experience presenting MOST to new audiences. The slides are designed to make comprehending and presenting MOST as easy as possible.

We also have available Teachers’ Corners for latent class analysis (LCA) and time varying effect modeling (TVEM).

Download the Teachers’ Corner or read more.

Video: Webinar on Analysis of Data From an MRT

September 20, 2018:

Thanks to all who participated in our 1 & 1 workshop on analysis of data from a micro-randomized trial (MRT). This is a video of the webinar that Methodology Center Principal Investigator Susan Murphy presented on Thursday, September 6, 2018. The video includes both the presentation and the question-and-answer session that followed. This is the second of two webinars on the MRT. Watch the first video before watching this one. These recordings are a great way to learn the basics of the MRT.

In an MRT, individuals are randomized hundreds or thousands of times over the course of the study. The goal of these trials is to assess the proximal, in-the-moment, impact of interventions (e.g., interventions that are intended to impact behavior over small time intervals). Through MRTs we can gather data to build optimized mHealth interventions.

Watch our website and eNews for information about upcoming 1 & 1 webinars.

Download the presentation slides.

Watch the video on YouTube.

Help Wanted!

September 18, 2018:hiring

The Methodology Center is seeking another methodologist to join our collaborative team. This is a research faculty position, open to candidates at the assistant or associate level. Candidates must have strong statistical programming skills, experience analyzing large, complex data sets, and familiarity with modern methods for handling and analyzing longitudinal data. Experience with mixture models, time-varying coefficient models, intensive longitudinal data, high-dimensional data, experimental design, and/or decision analysis is preferred.

The Methodology Center, located in Penn State’s College of Health and Human Development, serves as a national resource for the development and dissemination of innovative research methods. Research at The Methodology Center focuses on alcohol abuse, tobacco use, other drug abuse, and HIV, but it is broadly applicable across the social, health, and behavioral sciences. Methodology Center researchers draw upon and integrate methodological perspectives from a variety of disciplines, including statistics, engineering, psychology, and human development, to enable new categories of scientific research questions to be addressed. Our researchers enhance the quality of prevention and treatment research worldwide by providing behavioral scientists with innovative methods.

This is a rare opportunity to become a researcher in one of the best methodological research groups in the world. If you are self-motivated, detail-oriented, responsible, team-oriented, and creative, with excellent interpersonal, communication, and organizational skills, please apply.

This job is closed.

Webinar on PAMT Postdoctoral Fellowships

September 11, 2018:bcb

Join Methodology Center Associate Director Bethany Bray for an informational session about postdoctoral fellowships in the Prevention and Methodology Training program (PAMT). PAMT trains postdocs in both prevention science and statistical methodology and is funded by the National Institute on Drug Abuse through a T32 grant. The discussion will cover the purpose of PAMT, application process, advantages of the program, and expectations associated with receiving a fellowship. This webinar will be one hour in length; you can think of it as “30 & 30” rather than “1 & 1.” The information session will be held on Tuesday, November 6, from 3:30 to 4:30 p.m. Eastern Time.

PAMT produces scientists who are trained in the integration of prevention science and statistical methodology, and it offers a unique opportunity for postdoctoral researchers to continue their training under the mentorship of established researchers in both The Bennett Pierce Prevention Research Center and The Methodology Center in Penn State’s College of Health and Human Development.

The 1 & 1 will be hosted via Zoom webinar at https://psu.zoom.us/j/983416758.  Contact mchelpdesk@psu.edu if you have any questions. We hope you will join us.

Free Webinar on Multilevel Modeling

September 10, 2018:
mikeR
Join our upcoming 1 & 1 workshop, when Methodology Center Investigator Michael Russell will present an introduction to multilevel modeling (MLM) for intensive longitudinal data. 1 & 1 workshops consist of a one-hour live video presentation on a method followed by a one-hour question-and-answer session with the presenter. The workshop will be held on Wednesday, November 14, from 3:00 to 5:00 p.m. Eastern Time.

MLM is an extension of linear regression that adjusts for the statistical dependence that occurs when multiple observations are collected from each individual. It also allows the separation of within- and between-person associations. MLM is a powerful and flexible approach that allows users to specify a wide range of models and address diverse research questions using ILD. Michael will introduce MLM as a tool for answering questions about the within-person and between-person processes linking contextual and psychosocial factors to substance abuse risk.

The 1 & 1 will be hosted via Zoom webinar at https://psu.zoom.us/j/636351319. Contact mchelpdesk@psu.edu if you have any questions. We hope you will join us.

Free Webinar on Micro-Randomized Trials (Part 2)

August 13, 2018:susanm

Join our next 1 & 1 workshop, when Methodology Center Investigator Susan Murphy will present “Analyzing data from a micro-randomized trial (MRT).” 1 & 1 workshops consist of a one-hour live video presentation on a method followed by a one-hour question-and-answer session with the presenter. The workshop will be held on Thursday, September 6, from 3:00 to 5:00 p.m. Eastern Time. This webinar is a follow up to the webinar that Susan presented on June 14, 2018. For anyone who did not attend Susan’s first MRT workshop, we suggest watching the video of that webinar before joining us on September 6.

In an MRT, individuals are randomized hundreds or thousands of times over the course of a study. The goal of these trials is to optimize  mobile health interventions by assessing the effect of intervention components and assessing whether the intervention component effects vary with time or the individuals current context. Through MRTs we can gather data to build optimized just-in-time adaptive interventions (JITAIs). JITAIs are a type of adaptive intervention that can be delivered exactly when and where it is needed using smartphones and other mobile devices for their sensors and ability to communicate with patients.

The 1 & 1 will be hosted via Zoom webinar at https://psu.zoom.us/j/644882707. Contact mchelpdesk@psu.edu if you are unable to logon at the time of the workshop. We hope you will join us.