scholarly journals A Quantitative Framework for the Analysis of Two-Stage Exams

2018 ◽  
Vol 7 (4) ◽  
pp. 33 ◽  
Author(s):  
Andrew Martin
Keyword(s):  
Student Performance ◽  
Group Composition ◽  
Comprehensive Evaluation ◽  
Quantitative Estimation ◽  
Data Driven ◽  
Consensus Building ◽  
Two Stage ◽  
Positive Effects ◽  
Individual Preparation ◽  
Collaborative Skills

Two-stage exams have gained traction in education as a means of creating collaborative active-learning experiences in the classroom in a manner that advances learning, positively increases student engagement, and reduces test anxiety. Published analyses have focused almost exclusively on the increase in student scores from the first individual stage to the second collaboration stage and have shown clear positive effects on gains in student scores. Missing from these analyses is a comprehensive evaluation of the effects of individual preparation, the characteristics of questions, and small group composition on the outcomes two-stage exams. I developed a simple quantitative framework that provides a flexible approach for estimating and evaluating the effects of individuals, questions, and groups on student performance. Additionally, the framework yields statistics appropriate for making inferences about productive collaboration, consensus-building, and counter-productive interaction that happens within small groups. Analyses of 12 exams across two courses and 2 years using the quantitative framework revealed considerable variation for all three of these effects within and among exams. Overall, the results highlight the value of quantitative estimation of two-stage exams for gaining perspective on the effects of individuals, questions, and groups on student performance, and facilitates data-driven revision of assessments, curricula, and teaching strategies towards achieving gains in students' collaborative skills.  

scholarly journals Automated Data-Driven Generation of Personalized Pedagogical Interventions in Intelligent Tutoring Systems

2021 ◽  
Author(s):  
Ekaterina Kochmar ◽  
Dung Do Vu ◽  
Robert Belfer ◽  
Varun Gupta ◽  
Iulian Vlad Serban ◽  
...  
Keyword(s):  
Machine Learning ◽  
Student Performance ◽  
Language Processing ◽  
Intelligent Tutoring Systems ◽  
Large Scale ◽  
Intelligent Tutoring ◽  
Performance Outcomes ◽  
Data Driven ◽  
Personalized Feedback ◽  
Tutoring Systems

AbstractIntelligent tutoring systems (ITS) have been shown to be highly effective at promoting learning as compared to other computer-based instructional approaches. However, many ITS rely heavily on expert design and hand-crafted rules. This makes them difficult to build and transfer across domains and limits their potential efficacy. In this paper, we investigate how feedback in a large-scale ITS can be automatically generated in a data-driven way, and more specifically how personalization of feedback can lead to improvements in student performance outcomes. First, in this paper we propose a machine learning approach to generate personalized feedback in an automated way, which takes individual needs of students into account, while alleviating the need of expert intervention and design of hand-crafted rules. We leverage state-of-the-art machine learning and natural language processing techniques to provide students with personalized feedback using hints and Wikipedia-based explanations. Second, we demonstrate that personalized feedback leads to improved success rates at solving exercises in practice: our personalized feedback model is used in , a large-scale dialogue-based ITS with around 20,000 students launched in 2019. We present the results of experiments with students and show that the automated, data-driven, personalized feedback leads to a significant overall improvement of 22.95% in student performance outcomes and substantial improvements in the subjective evaluation of the feedback.

A Two-Stage Data-Driven-Based Prognostic Approach for Bearing Degradation Problem

2016 ◽  
Vol 12 (3) ◽  
pp. 924-932 ◽  
Author(s):  
Yu Wang ◽  
Yizhen Peng ◽  
Yanyang Zi ◽  
Xiaohang Jin ◽  
Kwok-Leung Tsui
Keyword(s):  
Data Driven ◽  
Two Stage ◽  
Degradation Problem

The Effect of Residential Mobility on Student Performance: Evidence From New York City

2019 ◽  
Vol 56 (4) ◽  
pp. 1380-1411 ◽  
Author(s):  
Sarah A. Cordes ◽  
Amy Ellen Schwartz ◽  
Leanna Stiefel
Keyword(s):  
New York ◽  
New York City ◽  
Student Performance ◽  
Residential Mobility ◽  
York City ◽  
Short Distance ◽  
Fixed Effects ◽  
Empirical Work ◽  
Long Distance ◽  
Positive Effects

Residential mobility is likely to have consequences for student performance, but prior empirical work is largely correlational and offers little insight into its impacts. Using rich, longitudinal data, we estimate the effects of residential mobility on the performance of New York City public school students. Using both student fixed effects and instrumental variables approaches, we find that long-distance moves have negative effects, while short-distance moves improve student performance. These differential effects are partially, but not fully, explained by school mobility. Rather, the positive effects of short-distance moves may be explained by improvements in housing, while the negative impacts of long-distance moves may be explained by lower performance relative to school peers and loss of social capital.

scholarly journals Teacher Turnover, Teacher Quality, and Student Achievement in DCPS

2016 ◽  
Vol 39 (1) ◽  
pp. 54-76 ◽  
Author(s):  
Melinda Adnot ◽  
Thomas Dee ◽  
Veronica Katz ◽  
James Wyckoff
Keyword(s):  
Student Achievement ◽  
Public Schools ◽  
Student Performance ◽  
Teacher Turnover ◽  
School Quality ◽  
Poor Performance ◽  
Negative Effects ◽  
Policy Regime ◽  
Positive Effects ◽  
Quasi Experimental

In practice, teacher turnover appears to have negative effects on school quality as measured by student performance. However, some simulations suggest that turnover can instead have large positive effects under a policy regime in which low-performing teachers can be accurately identified and replaced with more effective teachers. This study examines this question by evaluating the effects of teacher turnover on student achievement under IMPACT, the unique performance-assessment and incentive system in the District of Columbia Public Schools (DCPS). Employing a quasi-experimental design based on data from the first years of IMPACT, we find that, on average, DCPS replaced teachers who left with teachers who increased student achievement by 0.08 standard deviation ( SD) in math. When we isolate the effects of lower-performing teachers who were induced to leave DCPS for poor performance, we find that student achievement improves by larger and statistically significant amounts (i.e., 0.14 SD in reading and 0.21 SD in math). In contrast, the effect of exits by teachers not sanctioned under IMPACT is typically negative but not statistically significant.

A data-driven two-stage maintenance framework for degradation prediction in semiconductor manufacturing industries

2015 ◽  
Vol 85 ◽  
pp. 414-422 ◽  
Author(s):  
Ming Luo ◽  
Heng-Chao Yan ◽  
Bin Hu ◽  
Jun-Hong Zhou ◽  
Chee Khiang Pang
Keyword(s):  
Semiconductor Manufacturing ◽  
Manufacturing Industries ◽  
Data Driven ◽  
Two Stage
Sign in / Sign up

Export Citation Format

Share Document