Contrast

Examining Credit Recovery Learning Profile from Time-Series Clustering Analysis

Published on June 30, 2017
Written By: 

Jemma Bae KwonMichigan Virtual Learning Research Institute

The second report in the Credit Recovery series—Examining Credit Recovery Learning Profile from Time-Series Clustering Analysis—examines student learning behaviors in the first part of Algebra 2 courses. The ways that students engaged in coursework is targeted with two types of behavioral indicators, namely students’ attempted scores and the number of minutes spent in the learning management system (LMS) on a weekly basis.

The second report in the Credit Recovery series—Examining Credit Recovery Learning Profile from Time-Series Clustering Analysis—examines student learning behaviors in the first part of Algebra 2 courses. The ways that students engaged in coursework is targeted with two types of behavioral indicators, namely students’ attempted scores and the number of minutes spent in the learning management system (LMS) on a weekly basis.

The primary analytic strategy used in this study is time-series clustering, the process of partitioning time series data into groups based on mathematical distance among data points, so that time series in the same cluster can be construed as similar learning profiles.

Given the scarcity of research examining K-12 online learning, we decided to direct this first research on various learning profiles by using the hierarchical clustering approach rather than using a predetermined number of clusters for the hypothesized model under scrutiny.

The first report in the series – Examining Credit Recovery at a State Virtual School – is available here.

Download the Report

Table of Contents