skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Estimating the optimal treatment regime for student success programs.
We expand methods for estimating an optimal treatment regime (OTR) from the personalized medicine literature to educational data mining applications. As part of this development, we detail and modify the current state-of-the-art, assess the efcacy of the approaches for student success studies, and provide practitioners the machinery to apply the methods in their specifc problems. Our particular interest is to estimate an optimal treatment regime for students enrolled in an introductory statistics course at San Diego State University (SDSU). The available treatments are combinations of three programs SDSU implemented to foster student success in this large enrollment, bottleneck STEM course. We leverage tree-based reinforcement learning approaches based on either an inverse probability-weighted purity measure or an augmented probability-weighted purity measure. The thereby deduced OTR promises to signifcantly increase the average grade in the introductory course and also reveals the need for program recommendations to students as only very few, on their own, selected their optimal treatment.  more » « less
Award ID(s):
1633130
PAR ID:
10300857
Author(s) / Creator(s):
Date Published:
Journal Name:
Behaviormetrika
Volume:
48
ISSN:
0385-7417
Page Range / eLocation ID:
309-343
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Random forests are presented as an analytics foundation for educational data mining tasks. The focus is on course- and program-level analytics including evaluating pedagogical approaches and interventions and identifying and characterizing at-risk students. As part of this development, the concept of individualized treatment effects (ITE) is introduced as a method to provide personalized feedback to students. The ITE quantifies the effectiveness of intervention and/or instructional regimes for a particular student based on institutional student information and performance data. The proposed random forest framework and methods are illustrated on a study of the efficacy of a supplemental, weekly, one-unit problem-solving session in a large enrollment, bottleneck introductory statistics course. The analytics tools are used to identify factors for student success, characterize students benefitting from the supplemental instruction section, develop an objective criterion to, at the beginning of the semester, identify and advise these students into that section, and suggest intervention initiatives for at-risk groups in the course. 
    more » « less
  2. Abstract Introductory STEM courses represent entry points into a major, and student experiences in these courses can affect both their persistence and success in STEM disciplines. Identifying course-based student concerns may help instructors detect negative perceptions, areas of struggle, and potential barriers to success. Using an open-response survey question, we identified 13 common concerns expressed by students in introductory STEM courses. We converted these student-generated concerns into closed-ended items that were administered at the beginning and middle of the semester to students in 22 introductory STEM course sections across three different institutions. Students were asked to reflect on each item on a scale from very concerned to not concerned. A subset of these concerns was used to create a summary score of course-based concern for each student. Overall levels of student concern decreased from the first week to the middle of the semester; however, this pattern varied across different demographic groups. In particular, when controlling for initial concern and course grades, female students held higher levels of concern than their peers. Since student perceptions can impact their experiences, addressing concerns through communication and instructional practices may improve students’ overall experiences and facilitate their success. 
    more » « less
  3. Abstract Background Traditionally, doctoral student education in the biomedical sciences relies on didactic coursework to build a foundation of scientific knowledge and an apprenticeship model of training in the laboratory of an established investigator. Recent recommendations for revision of graduate training include the utilization of graduate student competencies to assess progress and the introduction of novel curricula focused on development of skills, rather than accumulation of facts. Evidence demonstrates that active learning approaches are effective. Several facets of active learning are components of problem-based learning (PBL), which is a teaching modality where student learning is self-directed toward solving problems in a relevant context. These concepts were combined and incorporated in creating a new introductory graduate course designed to develop scientific skills (student competencies) in matriculating doctoral students using a PBL format. Methods Evaluation of course effectiveness was measured using the principals of the Kirkpatrick Four Level Model of Evaluation. At the end of each course offering, students completed evaluation surveys on the course and instructors to assess their perceptions of training effectiveness. Pre- and post-tests assessing students’ proficiency in experimental design were used to measure student learning. Results The analysis of the outcomes of the course suggests the training is effective in improving experimental design. The course was well received by the students as measured by student evaluations (Kirkpatrick Model Level 1). Improved scores on post-tests indicate that the students learned from the experience (Kirkpatrick Model Level 2). A template is provided for the implementation of similar courses at other institutions. Conclusions This problem-based learning course appears effective in training newly matriculated graduate students in the required skills for designing experiments to test specific hypotheses, enhancing student preparation prior to initiation of their dissertation research. 
    more » « less
  4. Student-instructor interactions have an influence on student achievement and perceptions of learning. In college and university settings, large introductory STEM courses are increasingly including Peer-Led Team Learning (PLTL), an evidence-based technique associated with improved student achievement, recruitment, and retention in STEM fields, especially for underserved populations. Within this technique, peer leaders hold a unique position in a student’s education. Peer leaders have relevant experience in that they have had recent success in the courses in which they facilitate student learning, yet, compared to student-faculty or student-teaching assistant relationships, there is minimal imbalance of authority or power. Students might find their peer leaders to be more relatable than faculty or graduate teaching assistants, and may even consider them to be role models. We explored students’ perceptions of peer leader relatability and role model status in relation to students’ achievement and their perceived learning gains in the context of an introductory biology course with an associated PLTL program. The final course grades and self-assessed learning gains of PLTL students who felt they related to their peer leader were compared to those who did not. We also compared final course grades and self-assessed learning gains between PLTL students who viewed their peer leader as a role model versus those who did not. Self-reported learning gains were significantly higher for students who relate to their peer leader, as well as for students who viewed their peer leaders as a role model. There is some support that this trend is stronger for STEM majors versus those who are not enrolled in a STEM program, though the interaction is not significant. Significant differences in overall course grade were only observed between students who reported that they related to their peer leader versus those who did not relate to their peer leader. 
    more » « less
  5. Jones, Dyan; Ryan, Qing X.; Pawl, Andrew (Ed.)
    Designing physics courses that support students' activation and development of expert-like physics epistemologies is a significant goal of Physics Education Research. However, very little research has focused on how physics students' interactions with course structures resonate with different epistemological views. As part of a course redesign effort to increase student success in introductory physics, we interviewed introductory physics students about their experiences with course structures and their learning and belonging beliefs. We present here a case from this broader data corpus in which a student, Robyn, discusses his epistemological views of physics problem solving and his experiences with physics lectures, office hours, and discussion sections. We find that Robyn's physics epistemology manifests consistently across his interactions with each of these different course structures, suggesting a possible resonance between students' beliefs and their experiences with course structures and the value of further investigation into the potential merits of comprehensive course design. 
    more » « less