Measurement of change in health status with Rasch models.

Pasquale Anselmi,Giulio Vidotto,Ornella Bettinardi,Giorgio Bertolotti

doi:10.1186/s12955-014-0197-x

Pasquale Anselmi, Giulio Vidotto + Show 2 more

Open Access

https://doi.org/10.1186/s12955-014-0197-x

Copy DOI

Abstract

BackgroundThe traditional approach to the measurement of change presents important drawbacks (no information at individual level, ordinal scores, variance of the measurement instrument across time points), which Rasch models overcome. The article aims to illustrate the features of the measurement of change with Rasch models.MethodsTo illustrate the measurement of change using Rasch models, the quantitative data of a longitudinal study of heart-surgery patients (N = 98) were used. The scale “Perception of Positive Change” was used as an example of measurement instrument. All patients underwent cardiac rehabilitation, individual psychological intervention, and educational intervention. Nineteen patients also attended progressive muscle relaxation group trainings. The scale was administered before and after the interventions. Three Rasch approaches were used. Two separate analyses were run on the data from the two time points to test the invariance of the instrument. An analysis was run on the stacked data from both time points to measure change in a common frame of reference. Results of the latter analysis were compared with those of an analysis that removed the influence of local dependency on patient measures. Statistics t, χ2 and F were used for comparing the patient and item measures estimated in the Rasch analyses (a-priori α = .05). Infit, Outfit, R and item Strata were used for investigating Rasch model fit, reliability, and validity of the instrument.ResultsData of all 98 patients were included in the analyses. The instrument was reliable, valid, and substantively unidimensional (Infit, Outfit < 2 for all items, R = .84, item Strata range = 3.93-6.07). Changes in the functioning of the instrument occurred across the two time, which prevented the use of the two separate analyses to unambiguously measure change. Local dependency had a negligible effect on patient measures (p ≥ .8674). Thirteen patients improved, whereas 3 worsened. The patients who attended the relaxation group trainings did not report greater improvement than those who did not (p = .1007).ConclusionsRasch models represent a valid framework for the measurement of change and a useful complement to traditional approaches.

Highlights

IntroductionThe traditional approach to the measurement of change presents important drawbacks (no information at individual level, ordinal scores, variance of the measurement instrument across time points), which Rasch models overcome
The traditional approach to the measurement of change presents important drawbacks, which Rasch models overcome
In Rasch measurement, extreme response categories always approach a probability of 1 asymptotically because it is assumed that respondents with infinitely high measures must be observed in the highest categories regardless of the manner in which those categories are defined substantively or used by the sample [34]

Summary

Introduction

The traditional approach to the measurement of change presents important drawbacks (no information at individual level, ordinal scores, variance of the measurement instrument across time points), which Rasch models overcome. The article aims to illustrate the features of the measurement of change with Rasch models. Accurate measurement of change in health status is an essential requirement for maintaining and improving the quality of health services. Such measurement is usually accomplished using a single group repeated measures design, where patients are assessed before and after an intervention. Change scores are computed for each patient by taking the difference between his/her scores in the two time points. The measurement of change based on the aforementioned approach presents important drawbacks.

Methods

Results

Conclusion