Peer assessment via comparative judgement, David Sirl (School of Mathematical Science, University of Nottingham)
For the last few years I have included as a component of assessment in a 2nd year undergraduate probability module an exercise where student responses to an open-ended problem are peer-assessed using a “comparative judgement” (or “paired comparison”) procedure. the peer assessment element involves students comparing pairs of responses and choosing which demonstrates the better mathematical understanding. This “judgement” data is then fed into a statistical model (the Bradley-Terry model) which outputs scores which represent the relative “quality” of each response, and these are checked/moderated to ensure fairness/reasonableness.
I will describe what motivates me to do it, how it actually works, with the twin aims of (i) informing about what seems a little-known method of assessment and (ii) provoking discussion about the method’s pros and cons (there being a strictly positive number of both).
Registration
If you will be joining the talk online then please register here . If you are an IMA Member or you have previously registered for an IMA conference, then you are already on our database. Please “request a new password” using the email address previously used, to log in. Non IMA Members welcome!
Online joining information will be sent one day prior.
If you will be joining in person, no need to register please head to the venue on the day – LT907, Livingstone Tower,26 Richmond Street, University of Strathclyde.
Image Credit: Photo by Photo by Kenny Eliason on Unsplash / CC BY-NC 2.0
