Skip to main content
. Author manuscript; available in PMC: 2017 Jun 21.
Published in final edited form as: Psychol Test Assess Model. 2016;58(1):183–219.

Table 8. PROMIS anxiety short form item set: Differential item function (DIF) results: Education subgroup comparisons.

Item description IRTPRO lordif Magnitude (NCDIF) Effect Size T1
GD vs. CD GD vs. Some Coll. GD vs. HS GD vs. NoHS GD vs. CD GD vs. Some Coll. GD vs. HS GD vs. NoHS GD vs. CD GD vs. Some Coll. GD vs. HS GD vs. NoHS GD vs. CD GD vs. Some Coll. GD vs. HS GD vs. NoHS
I felt fearful NU; U* U* 0.0004 0.0026 0.0063 0.0142 -0.0079 0.0307 0.0605 0.0982
I felt anxious U U* U* NU*; U* U* U* U* 0.0060 0.0199 0.0352 0.0905 0.0514 0.0998 0.1423 0.2468
I felt worried NU U* NU*; U* U* 0.0000 0.0020 0.0037 0.0100 -0.0005 0.0066 0.0439 0.0790
I found it hard to focus on anything other than my anxiety NU; U* U* NU; U* 0.0028 0.0029 0.0156 0.0164 -0.0353 -0.0320 -0.0979 -0.0847
I felt nervous NU U* U* 0.0006 0.0003 0.0031 0.0172 -0.0038 -0.0068 -0.0336 -0.1159
I felt uneasy U U* NU; U* 0.0009 0.0035 0.0039 0.0035 0.0155 0.0401 0.0338 0.0219
I felt tense U U* U* U U* 0.0023 0.0063 0.0117 0.0110 0.0356 0.0587 0.0821 0.0864
My worries overwhelmed me NU; U* NU; U* 0.0024 0.0028 0.0127 0.0173 -0.0338 -0.0399 -0.0863 -0.1052
I felt like I needed help for my anxiety NU NU NU NU U* 0.0077 0.0066 0.0175 0.0054 0.0132 0.0359 0.0471 0.0290
Many situations made me worry NU; U U U* U* 0.0068 0.0141 0.0370 0.0354 -0.0514 -0.0966 -0.1605 -0.1590
I had difficulty calming down U* NU; U* 0.0027 0.0038 0.0105 0.0200 -0.0310 -0.0227 -0.0660 -0.1141

All NCDIF values were smaller than the threshold (0.0960)

Indicates value above threshold of 0.10; bolded values are above 0.15.

*

Asterisks indicate significance after adjustment for multiple comparisons.

NU= Non-uniform DIF involving the discrimination parameters; U=Uniform DIF involving the location parameters.

GD = graduate degree; CD = college degree; Coll. = college; HS = high school

For the lordif analyses, the Uniform and non-uniform DIF was determined using the likelihood ratio chi-square test. Uniform DIF is obtained by comparing the log likelihood values from models one and two. Non-uniform DIF is obtained by comparing the log likelihood values from models two and three. DIF was not detected using the pseudo R2 measures or the change in Beta criterion.