Rasch analysis of the gross motor function measure: validating the assumptions of the rasch model to create an interval-level Measure1 Lisa M Avery, BEng, Dianne J Russell, MSc, Parminder S Raina, PhD, Stephen D Walter, PhD, Peter L Rosenbaum, MD, FRCP(C) Archives of Physical Medicine and Rehabilitation Volume 84, Issue 5, Pages 697-705 (May 2003) DOI: 10.1016/S0003-9993(02)04896-7
Fig 1 The decision process used to select the most appropriate Rasch model for the GMFM. Note that all models are discussed elsewhere.10 Archives of Physical Medicine and Rehabilitation 2003 84, 697-705DOI: (10.1016/S0003-9993(02)04896-7)
Fig 2 Illustration of the algorithm used to score the GMFM-66. Archives of Physical Medicine and Rehabilitation 2003 84, 697-705DOI: (10.1016/S0003-9993(02)04896-7)
Fig 3 Illustration of the agreement between true and estimated ability over 100 simulations for varying numbers of items tested. Archives of Physical Medicine and Rehabilitation 2003 84, 697-705DOI: (10.1016/S0003-9993(02)04896-7)
Fig 4 Example of an item map by difficulty order for the GMFM-66. Archives of Physical Medicine and Rehabilitation 2003 84, 697-705DOI: (10.1016/S0003-9993(02)04896-7)