Doing data analysis: Some tools and techniques
Paul Collett, Trevor Holster
Collett gave us an introduction to the R statistical package. With a huge user base of smart statisticians, R is also much cheaper than comparable programs; it's free and easy to download (one click for Mac) and use, though commands have to be typed in like the original DOS programs. All packages have Help PDF files included and there are many tutorials, books and guides. Input data is standard Excel format. He ran us through a survey – of reliability tests measuring different aspects of the scale of self-regulated learners, pointing out that the system saves all past entries, facilitating returning to a project at any stage, and then showed how to use the package for various types of data analysis. Holster's presentation reviewed Rasch's simple concept of "specific objectivity" (to gain a more objective picture of student performance than raw scores can give us by seeing how such things as rater bias and item difficulty affect those scores for a specific test/task) and then demonstrated Rasch analysis using data from a multiple-choice vocabulary test and from judged ratings of classroom presentations.
Link to meeting listing

Next Item Previous Item