Skip to main content
. Author manuscript; available in PMC: 2018 Aug 1.
Published in final edited form as: Mov Disord. 2017 Jun 1;32(8):1244–1249. doi: 10.1002/mds.27058

Table 1.

Gender- and Education-Based Statistically Significant DIF

Item MIMIC p-
values
LORDIF p-
values
R2 Magnitude

Gender-Based Non-Uniform DIF

Historical Disability Speech <0.0005 0.0001 0.0019 Negligible

Objective Disability Communication <0.0005 <0.00005 0.0025 Negligible

Gender-Based Uniform DIF

Historical Disability Time Spent with On-Dyskinesia <0.0005 0.0005 0.0015 Negligible

Education-Based Non-Uniform DIF

None NA NA NA NA

Education-Based Uniform DIF

Historical Disability Time Spent with On-Dyskinesia
    <7 vs. all others <0.0005 <0.00005 0.003 Negligible

Historical Disability Chewing/Swallowing
    >12 vs. all others <0.0005 <0.00005 0.0035 Negligible

Historical Disability Eating tasks
    >12 vs. all others <0.0005 0.00001 0.0021 Negligible

Historical Disability Dressing
    >12 vs. all others <0.0005 <0.00005 0.0031 Negligible

Historical Disability Hygiene
    <7 vs. all others <0.0005 <0.00005 0.0057 Negligible
    >12 vs. all others <0.0005 <0.00005 0.0079 Negligible

Legend: Most of the UDysRS items did not meet the minimal statistical criteria for DIF (see text). The Table lists items with DIF identified by both lordif and MIMIC as independent approaches (p values shown) with McFadden’s R2 (R2) indicating the impact of the DIF.