NWEA implementation of automated item generation (AIG) alongside traditional item-development approaches¶

Element · All elements
Evidence · no claims cited

Description¶

This element is an NWEA presentation, dated September 2020, that summarizes the organization's work implementing automated item generation (AIG). The abstract states it "summarizes the work that's been done at NWEA to implement automated item generation (AIG), in addition to traditional approaches, to leverage the future." AIG is presented as a complement to, not a replacement for, traditional item development, with an equity motivation for measurement. The supplied text is an abstract page only, so no methods, findings, or psychometric results are available from it.

Design Implications¶

Context¶

Requirements¶

• The presentation is positioned as requiring both AIG implementation work and continued use of traditional item-development approaches, per the phrase "in addition to traditional approaches".

Constraints¶

• The supplied text is a short abstract page; it reports no empirical results, validation evidence, or implementation details about the AIG work.

Target Learners¶

• K-12 students assessed with NWEA assessments

Target Learning Goals¶

• Equitable and valid measurement of student achievement through assessment item development

Related Elements¶

• NCME 2020 presentation on effort-moderated IRT parameter estimation accuracy

Examples¶

-

Key Sources¶

• Sarah Miller, Sylvia Scheuring, Abby Javurek, Jake McMillen, Emily Bo, Mary Ann Simpson. (2020). Automated item generation (AIG): A future for more equitable measurement. NWEA presentation. https://www.nwea.org/research/publication/automated-item-generation-aig-a-future-for-more-equitable-measurement/