Norwegian version of this page

Log-file Analysis in International Large-Scale Assessments (LOGAN)

Table of numbers and graphs showing results from assessments

How do we extract and analyze log data from computer-based assessments? The LOGAN project has the answer. Photo: Luke Chesser/Unsplash

About the project

A new type of data is emerging from digital-based assessments through computer-generated log files. Gathering the traces of users’ interactions with the test software, these time-stamped files (a.k.a. “log files”) can provide a wealthy source of information beyond the traditional correct/incorrect answers to the test items. This project aims to develop statistical tools for the analysis of log-file data from international surveys such as the Programme of International Student Assessment (PISA) and the Programme for International Assessment of Adult Competencies (PIAAC). Through the development of an open-source R package called LOGAN, this project is an evolving portfolio of research targeting the extraction and analysis of meaningful features from these files.

Background

Despite the availability of public log-file data from computer-based tests, there is still a lack of software that adequately deals with this kind of data. The LOGAN package was created to fill this gap, looking into the particularities of international large-scale assessments data.

Financing

This project is financed by CEMO.

Cooperation

Research group FREMO.

Tools

Please find the latest stable version of the LOGAN software and documentation here:

https://cran.r-project.org/web/packages/LOGAN/index.html

Development versions of the package can be accessed on:

https://github.com/derecost/LOGAN

Published June 12, 2019 10:06 AM - Last modified June 17, 2019 2:49 PM

Contact

Project leader: Denise Reis Costa