Research report

MAP Growth K–2 item fit analysis study

2019

By: Wei He

Description

Item fit analysis examines how accurately observed response data fit the underlying model. In test analysis, item fit can be used to validate the calibration process of item parameters. The purpose of this study is to examine the fit of MAP Growth K–2 items involved in a scale alignment study conducted by NWEA to realign the scales underlying the MAP Growth K–2 and MAP Growth 2–5 Reading and Mathematics tests. Part of that study involved adjusting the difficulties of MAP Growth K–2 items (i.e., each item’s Rasch Unit (RIT) value) using growth model predictions from longitudinal test results. To make sure the items with the adjusted RIT values still fit the underlying Rasch model, this study examines the model-data fit of these items using two different samples. Specifically, for each sample, infit and outfit indices, along with point measure correlations were calculated, followed by a comparison of how these indices differ using the old and new (i.e., original and adjusted) item difficulties and person ability estimates. The results from the different samples were also compared with each other.

See More
View Asset

Related Topics