January 27, 2016
In this podcast, we discuss the application of the multiphase optimization strategy (MOST) to the development of an online intervention to reduce sexual risk behavior among college students. Host Aaron Wagner speaks with Kari Kugler, Methodology Center investigator, and Amanda Tanner, assistant professor of public health education at University of North Carolina at Greensboro (UNCG), about the project which is funded by the National Institute on Alcohol Abuse and Alcoholism.
January 27, 2016
January 20, 2016
Congratulations to Runze Li for being named a Highly Cited Researcher by Thomson Reuters for the second consecutive year. Runze's work is characterized as "mathematics" (which is extremely broad), and he is still one of only 99 researchers from his field to be designated as "Highly Cited." During Runze's 13 years at The Methodology Center, he has pioneered new statistical methods and worked to translate and disseminate those methods to behavioral researchers. His research focuses on the analysis of intensive longitudinal data (ILD) and high-dimensional data. He led the development of Methodology Center software for variable selection in high-dimensional data and software for analyzing ILD, including a SAS macro for time varying-effect modeling. Runze shows no signs of slowing down, so he might appear on this list for years to come. Congratulations, Runze!
January 13, 2016
The Methodology Center is pleased to release the latest version (2.0) of the SAS LCA Graphics Macros for use with PROC LCA. The latest version includes a bug fix. SAS and PROC LCA are required to use these macros. For an overview of the functionality, please visit the download page.
December 2, 2015
We are pleased to announce the release of a new web applet helpful when conducting factorial experiments and fractional factorial experiments. The applet produces a list of random numbers that can be used to assign subjects to experimental conditions. When the applet is used properly, subjects will be spread as evenly as possible across conditions. Factorial and fractional factorial experiments are useful for selecting the components to be included in an intervention when scientists are following the multiphase optimization strategy (MOST).
November 23, 2015
Congratulations to the team of researchers from The Methodology Center and North Carolina State University on their recently awarded grant from the National Institute on Alcohol Abuse and Alcoholism, “Data-Based Methods for Just-in-Time Adaptive Interventions in Alcohol Use.” Despite the many problems associated with alcohol abuse, relatively few people in the United States receive treatment for alcohol use disorders. Using smartphones to deliver interventions will allow more people to be treated, and will reduce the cost of treatment. This project aims to develop the methods and algorithms needed to provide each individual with the proper intervention exactly when he or she needs it.
November 11, 2015
Research has shown that some adolescents experience nicotine dependence at low levels of smoking (DiFranza et al., 2000; O'Loughlin et al., 2003). Other results indicate that early nicotine dependence strongly predicts future smoking (Dierker & Mermelstein, 2010; DiFranza et al., 2002). A recent paper in the journal Addictive Behavior, “Nicotine-dependence-varying effects of smoking events on momentary mood changes among adolescents,” provides insight into the mechanisms that encourage and maintain nicotine dependence. In this paper, the authors apply time-varying effect modeling (TVEM) and other methods to examine the association between nicotine dependence and the impact of smoking on mood. Authors include Methodology Center investigators, affiliates, and collaborators Arielle Selya, Nicole Updegrove, Jennifer Rose, Lisa Dierker, Xianming Tan, Donald Hedeker, Runze Li, and Robin Mermelstein.
October 14, 2015
The latest version of the TVEM (time-varying effect modeling) SAS macro (v. 3.1.0) offers several improvements over the previous version (v 2.1.1). Three macros from the previous suite have been consolidated into a single macro with simplified syntax for ease of use. Also, the new macro has the ability to model within-subject correlation using random effects or a robust sandwich variance estimator. Other improvements have been made to the onscreen output, the ability to generate output datasets, and the ability to generate plots in different ways.
TVEM allows researchers to answer new questions using intensive longitudinal data and mature panel studies, as well as answer questions about age-varying effects using less intensive data.
October 12, 2015
Early milestones in the development of smoking, such as first cigarette, experimental smoking, and onset of regular smoking, are key risk factors for later nicotine dependence (Dierker et al., 2008). The risk associated with age of smoking initiation has been studied widely, but less research has examined the link between the age of onset of regular smoking and later dependence. In a new article to appear in Addictive Behaviors, Methodology Center Investigators Stephanie Lanza and Sara Vasilenko apply time varying effect modeling (TVEM) to explore the link between age of onset of regular smoking and adult nicotine dependence.
This brief article is the first to apply TVEM to explore the complex association between the age of onset of a risky behavior and later diagnosis.
October 9, 2015
Methodology Center research associate Kari Kugler is interested in the development of effective and efficient interventions to improve sexual and reproductive health outcomes among adolescents and young adults. For the last four years, she has worked closely with Methodology Center Director Linda Collins to develop applications of the multiphase optimization strategy (MOST), an engineering-based framework for optimizing interventions.
September 28, 2015
Congratulations to the team of researchers from The Methodology Center and University of North Carolina at Greensboro (UNCG) on their recently awarded grant, “Engineering an Online STI Prevention Program.” One in four students will be diagnosed with a sexually transmitted infection (STI) over the course of their collegiate careers. Binge drinking, which is common among college students, contributes to STI risk factors like casual sex, unprotected sex, and multiple-partner sexual experiences. The research team for this National Institute on Alcohol Abuse and Alcoholism-funded project will use the multiphase optimization strategy (MOST) to design an optimized, internet-based intervention that targets the intersection of alcohol use and risky sex among college students.