ACTNext shows that Bayesian knowledge tracing (BKT) and item response theory (IRT) are intimately connected
IOWA CITY, IA—A new research report by ACTNext reveals
a critical relationship between learning and assessment that may lead to new
ways to measure student achievement—with potentially profound implications for
education.
The report, Assessment meets Learning: On the Relation between Item Response Theory and Bayesian Knowledge Tracing, shows, for
the first time ever, a mathematical relationship between the Bayesian Knowledge
Tracing (BKT) learning model, which tracks knowledge acquisition on a continual
basis, and the Item Response Theory (IRT) assessment model, which is used to
estimate how much students have learned.
“This development will help better measure student success for students, teachers and administrators, districts, and states,” said ACT CEO Marten Roorda. “It is groundbreaking research that we believe will help change the field of education as a whole for the better.”
Connecting a learning model to an assessment model
may lead to new ways to assess student learning through the work students are already
doing in the classroom. By tracking a learners’ achievement continuously
through a learning system, it is possible to get an estimate of summative
learning that would otherwise be obtained only through an end-of-course exam.
“Students already do assignments, homework, quizzes, and tests all year long in their classes, and these findings suggest we can use those data to assess student learning,” said Alina von Davier, ACT senior vice president of ACTNext. “This can provide educators with benchmarks to use throughout the year, as well as at the end, that will help them measure what students have achieved academically.”
ACTNext believes that identifying the relationship
between the two models will eventually lead to a connection between learning and
assessment and education. The
findings of this research puts computational psychometrics closer to achieving
that goal.
“ACT is on the cutting edge of learning and measurement, as we work to transform the field of educational assessment and find new ways to help students learn the skills they need to succeed in college and career,” said Roorda. “This research is a stepping stone to broader and more important connections between learning, assessment, and education. We’re not there yet, but we are making incredible strides in that direction.”
The report, authored by Gunter Maris, ACTNext
senior director of advanced psychometrics, Benjamin Doenovic, ACTNext research
scientist, and colleagues, has been submitted for review, and can be accessed
for free here.
Follow ACTNext
About ACTNext
Led by computational psychometrics researcher Alina von Davier, ACTNext™ is the research, development, and business innovation division at ACT. The ACTNext research team, comprised of leaders working on innovative solutions that advance individuals throughout their lifetimes, is passionate about making a difference.
