Combining Item Purification and Multiple Comparison Adjustment Methods in Detection of Differential Item Functioning.

Many of the differential item functioning (DIF) detection methods rely on a principle of testing for DIF item by item, while considering the rest of the items or at least some of them being DIF-free. Computational algorithms of these DIF detection methods involve the selection of DIF-free items in an iterative procedure called item purification. Another aspect is the need to correct for multiple comparisons, which can be done with a number of existing multiple comparison adjustment methods. In this article, we demonstrate that implementation of these two controlling procedures together may have an impact on which items are detected as DIF items. We propose an iterative algorithm combining item purification and adjustment for multiple comparisons. Pleasant properties of the newly proposed algorithm are shown with a simulation study. The method is demonstrated on a real data example.

Long-term cognitive trajectory and activities of daily living in healthy aging.

OBJECTIVE: The purpose of the present study was to investigate if participants in NANOK study (National Normative Study of Cognitive Determinants of Healthy Ageing) who show no cognitive decline throughout five years (successful healthy agers; SHA) will show less age-related differences in instrumental activities of daily living (IADL) based on Functional Activities Questionnaire in comparison to participants who show subtle cognitive decline (Decliners) over time. METHOD: We used two different classifications of SHA: Rogalski (N = 25 SHA and N = 15 Decliners) based on cross-sectional neuropsychology measures and linear mixed model (LMEM; 20 SHA and 20 Decliners) based on the Montreal Cognitive Assessment longitudinal 5-years follow-up. Whole-brain T1- and T2-weighted images were corrected for distortions and segmented using Freesurfer. Whole-brain volumetry was performed using FSL's voxel-based morphometry tool. RESULTS: The cognitive decline after four years follow-up but not age predicts subtle impairment in IADL in healthy ageing participants. We found brain volumetric differences between SHA and Decliners based on Rogalski but not LMEM classification especially in bilateral insular cortices and ventrolateral frontal cortex. The logistic regression model achieved an accuracy of 75% for the Rogalski in comparison to 67.5% for the LMEM classification. CONCLUSIONS: Slight restrictions in IADL seem to be a useful tool for screening healthy ageing participants at risk of developing subtle cognitive decline over a period of five years and the cross-sectional Rogalski criteria based on standardized neuropsychological measures were superior for tapping age-related brain changes to longitudinal LMEM classification based on screening (Montreal Cognitive Assessment).