I am currently a third year Ph.D candidate in the Quantitative Psychology program at the University of Virginia. I am working in the Mathematical Psychology Lab, where Timo von Oertzen is my advisor. I also spend time working in the Social Development Lab in the Curry School of Education with my secondary advisor, Sara Rimm-Kaufman, and in the Implicit Social Cognition Lab with Brian Nosek. I earned bachelor degrees in Applied Mathematics and Psychology from the University of Rhode Island, and plan to develop these interests further in graduate school.

The Meta-Science of Data Analysis in Behavioral Research

As a quantitative psychologist, a big research interest of mine involves the meta-science of data analytics, or in simpler terms, how data analysis is being used in present-day behavioral research. My main focus is how common techniques and paradigms can implement small improvements to reap large benefits in terms of statistical power, parameter bias, and increased likelihood of replicability. For example, the Implicit Association Test (IAT) is a widely used test in social psychology and yields a large time series of reaction times for each participant. IAT data is typically analyzed by aggregating each participant's time series to a single value. With Dr. Michael Kubovy and colleagues, I am examining how more flexible analytic methods the incorporate the entire time series, such as mixed-effects models, might yield improvements compared to the more traditional methods of aggregation.

Exploratory Data Analysis for Longitudinal Data

The incorporation of exploratory longitudinal analysis techniques, namely identifying hetereogeneous sub-populations based on longitudinal trajectories, can provide new avenues to answer theoretically interesting research questions that often remain unanswered after traditional confirmatory measures have already been exhausted. While many techniques of varying complexity exist, it can be difficult to determine which methods work best in what situations. My pre-dissertation involves comparing these methods on simulated data across a number of varying dataset conditions, such as number of sub-groups, statistical noise, effect size of parameters, etc., to determine: 1) Which methods are superior in what situations? and 2) Under what circumstances are more complex modeling techniques better than more parsimonious ones?

Student Engagement in Elementary School Mathematics

My experiences as a mathematics tutor and teaching assistant at the University of Rhode Island has made me interested in developing better teaching methods for statistics/math as well as the understanding the current state of STEM education in schools. To gain such substantive experience, I collaborate with Dr. Sara Rimm-Kaufman's Social Development Lab in the Curry School of Education to assess the Responsive Classroom approach as it relates to math achievement in elementary school children. I am currently working on a independent project to see how different profiles of students (based on cognitive ability, feelings toward school, and mathematics self-efficacy), might be differentially affected in their learning outcomes by classroom organization.

STEM Engagement in College Mathematics

Success in college mathematics is essential for a strong STEM workforce as such classes are "pipelines" to the hard-science disciplines. Many projects on STEM engagement involve the assessment of instructional methods and/or explicit psychological measures, but do not take into account implicit measures of bias (i.e. associating math-male significantly more than math-female) that still pervade our culture. I am currently collaborating with Brian Nosek and Fred Smyth on the Full Potential Initiative to better understand how these implicit biases in the college environment may be related to shaping personal identities and contributing to an individual's intent to stay involved in STEM-related classes and other activities.

Research Methods & Data Analysis II Lab, Spring 2013

Department of Psychology, University of Virginia
Select Teaching Evaluations

Research Methods & Data Analysis I Lab, Fall 2012
Department of Psychology, University of Virginia
Select Teaching Evaluations

Honors Quantitative Methods in Psychology, Spring 2011
Department of Psychology, University of Rhode Island

URI 101 Co-Instructor, Fall 2010
Office of Internships and Experiential Education, University of Rhode Island

Dan Martin


    102 Gilmer Hall
    University of Virginia
    P.O. Box 400400
    Charlottesville, VA 22904
    dm4zz at virginia dot edu