Enhancing Simulation-based Training Adversary Tactics via Evolution (ESTATE)

Abstract

The goal of this task is to discover a method to measure student learning and to determine if students are gaining proficiency in this pre-algebra activity. This method will augment our student assessment and challenge adaptation techniques by providing a better estimate of student ability and Zone of Proximal Development (ZPD). Earlier exploration of the MoneyBee Dataset indicated that the students score better as they attempt more problems, but because of student selection of problems, it was unclear whether the students were improving or simply choosing easier problems to attempt (Rosenberg, 2009). Also, we discovered that our heuristic estimate of problem difficulty correlates with the time to complete a problem (Rosenberg, 2010). The results of the current analysis below show that as the number of problems attempted by a student increases, 1) the mean and median difficulty increases and 2) the mean and median time to complete decreases. This provides strong evidence for learning on the MoneyBee task.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 15, 2010
Accession Number
ADA523231

Entities

People

  • Brad R Rosenberg

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Contracts
  • Data Analysis
  • Debugging
  • Environment
  • Information Operations
  • Learning
  • Models
  • Personal Information Managers
  • Simulations
  • Students
  • Trainees
  • Training
  • User Interface
  • Visualizations

Fields of Study

  • Education

Readers

  • Artificial Intelligence
  • Military Training and Readiness Simulation
  • Systems Analysis and Design