Dichotomous Rasch model analysis learning curve endoscopic lumbar decompression.
| Model Fit | |||
| Person Reliability | MADaP3a | P | |
| Scale | 0.691 | 0.285 | <0.001 |
| Endoscopic Lumbar Learning Curve Item Statistics | |||
| CPT Code | Measure | Infitb | Outfitc |
| 63047 | −0.994 | 1.226 | 1.310 |
| 22102 | −1.662 | 0.991 | 0.754 |
| 63030 | −0.890 | 1.234 | 1.106 |
| 63005 | −1.784 | 1.130 | 1.017 |
| 63620 | −0.482 | 1.166 | 1.240 |
| 22869 | −1.544 | 1.009 | 0.951 |
| 22630 | −1.100 | 0.751 | 0.498 |
| 22612 | −1.318 | 0.726 | 0.468 |
| 22532 | −0.583 | 0.908 | 0.658 |
| 22533 | −0.994 | 0.897 | 0.658 |
| 22633 | −0.994 | 0.988 | 0.756 |
Abbreviation: CPT, Current Procedural Terminology.
↵a MADaQ3 = Mean of absolute values of centered Q_3 statistic with P value obtained by Holm adjustment
↵b Infit = Information-weighted mean square based on the χ2 statistic with each observation weighted by its statistical information (model variance). This is more sensitive to unexpected patterns of observations by persons on items that are roughly targeted on them (and vice versa).
↵c Outfit = Outlier-sensitive means square statistic is more sensitive to unexpected observations by surgeons. Infit and outfit data between 0.6 and 1.4 indicate good fit of the Rasch model. Infit and outfit numbers outside this range suggest the presence of confounding factors, such as for CPT codes 22630 and 22612.