SEARCH

SEARCH BY CITATION

Although population modeling methods are well established, a paucity of literature appears to exist regarding the effect of missing background data on subpopulation achievement estimates. Using simulated data that follows typical large-scale assessment designs with known parameters and a number of missing conditions, this paper examines the extent to which missing background data impacts subpopulation achievement estimates. In particular, the paper compares achievement estimates under a model with fully observed background data to achievement estimates for a variety of missing background data conditions. The findings suggest that sub-population differences are preserved under all analyzed conditions while point estimates for subpopulation achievement values are influenced by missing at random conditions. Implications for cross-population comparisons are discussed.