Skip to main content

Table 3 The results of the hybrid OLR/IRT DIF analysis across fathers and daughters on the PedsQL™ 4.0 (Empirical threshold values from Monte Carlo simulations is also reported)

From: Assessing the effect of child’s gender on their father–mother perception of the PedsQL™ 4.0 questionnaire: an iterative hybrid ordinal logistic regression/item response theory approach with Monte Carlo simulation

  Non-uniform Uniform
Pa Thresholdb ΔR2c Thresholdd Pa Thresholdb ΔR2c Thresholdd CvBLe Thresholdf
Physical health
5. Hard to take a bath or shower 0.0749 0.0071 0.0052 0.0118 0.0000 0.0080 0.0383 0.0113 0.0604 0.0327
Emotional functioning
2. Feel sad or blue 0.0001 0.0179 0.0094 0.0036 0.0000 0.0102 0.0355 0.0041 0.0935 0.0111
5. Worry about what will happen 0.5410 0.0154 0.0002 0.0034 0.0000 0.0080 0.0317 0.0040 0.0668 0.0115
Social functioning
1. Trouble getting along with peers 0.0694 0.0311 0.0025 0.0037 0.0000 0.0122 0.0156 0.0049 0.0241 0.0131
3. Teased 0.2442 0.0188 0.0023 0.0097 0.0000 0.0086 0.0286 0.0122 0.0633 0.0277
4. Doing things other peers do School 0.0000 0.0172 0.0189 0.0061 0.0000 0.0138 0.0321 0.0067 0.0760 0.0176
5. Hard to keep up when play with others 0.2014 0.0237 0.0012 0.0040 0.0000 0.0063 0.0408 0.0059 0.0883 0.0154
School functioning
1. Hard to concentrate 0.0000 0.0204 0.0543 0.0038 0.0850 0.0070 0.0020 0.0051 0.0014 0.0126
2. Forget things 0.0000 0.0186 0.0176 0.0039 0.0001 0.0089 0.0111 0.0048 0.0106 0.0152
3. Trouble keeping up with schoolwork 0.0525 0.0133 0.0032 0.0059 0.0000 0.0100 0.0578 0.0060 0.1251 0.0167
  1. Italic numbers represent the items showing uniform or non-uniform DIF
  2. aP value of Chi-square test of difference between the Models 1 and 2, and Models 2 and 3 for testing uniform and non-uniform DIF, respectively
  3. bThreshold values for the nominal α level associated with Chi-square test of difference between the Models 1 and 2, and Models 2 and 3
  4. cΔR2 is the R2 difference between the Models 1 and 2, and Models 2 and 3 for testing uniform and non-uniform DIF, respectively
  5. dThreshold values for ΔR2, difference between the Models 1 and 2, and Models 2 and 3 for testing uniform and non-uniform DIF, respectively
  6. eCrane, van Belle and Larson criterion—CvBL: |β1 (Model 1) − β1 (Model 2)/β1 (Model 1)|
  7. fThreshold values of Crane, van Belle and Larson criterion—CvBL: |β1 (Model 1) − β1 (Model 2)/β1 (Model 1)|