Is there a way to calculate reliability when items are randomly selected for delivery in a classical test theory (CTT) model? Psychometrician Austin Fossey offers his thoughts.
Phychometrician Austin Fossey looks under the hood to see if the changes in subscores reflect the actual results from the training, and shares his analysis and best practices.
Preserve the validity of your assessments! In this post, Psychometrician Austin Fossey lists 4 ways to identify when a content breach has occurred so that the problem can be remedied through changes to the assessment or disciplinary actions against the parties involved in the breach.
Psychometrician Austin Fossey offers an example to help explain how to use item discrimination as the primary statistic for item selection in classical test theory (CTT). You can check out Austin's thorough explanation in the blog post.
Psychometrician Austin Fossey writes about the question type report: "This report can provide a quick profile of the population of the item bank or a topic when needed, though more detailed item tracking by status, topic, metatags, item type, and exposure is advisable for anyone managing a large-scale item development project." Read the article for some potential use cases for this simple report.
If you work with assessment statistics or just about any branch of social science, you may be familiar with Simpson’s paradox—the idea that data trends between subgroups change or disappear when the subgroups are aggregated. There are hundreds of examples of Simpson’s paradox, but for the sake of illustration, here is a simple example from Psychometrician Austin Fossey.
Psychometrician Austin Fossey believes negative scores are not appropriate for most classical test theory (CTT) assessment designs, because they do not add measurement value, and they are difficult to interpret. Read more about Austin's argument including: Measurement value and interpretation issues of negative item scores.
The final step in item development is the psychometric review, which is designed to flag any items that may need to be removed before you build your assessment forms for production.
In this blog post, Psychometrician Austin Fossey digs into difficulty, discrimination, and bias to figure out what is wrong with items that return poor statistics.
Do you trust the results of your test? Like many questions in psychometrics, the answer is that it depends. Read more from Psychometrician Austin Fossey on the faith we put in the testing body in order to have trustworthy assessment results.