Refine
Document Type
Language
- English (5) (remove)
Has Fulltext
- no (5)
Is part of the Bibliography
- no (5)
Keywords
- Rasch analysis (5) (remove)
The Impact of Missing Values and Single Imputation upon Rasch Analysis Outcomes: A Simulation Study
(2018)
Imputation becomes common practice through availability of easy-to-use algorithms and software. This study aims to determine if different imputation strategies are robust to the extent and type of missingness, local item dependencies (LID), differential item functioning (DIF), and misfit when doing a Rasch analysis. Four samples were simulated and represented a sample with good metric properties, a sample with LID, a sample with DIF, and a sample with LID and DIF. Missing values were generated with increasing proportion and were either missing at random or completely at random. Four imputation techniques were applied before Rasch analysis and deviation of the results and the quality of fit compared. Imputation strategies showed good performance with less than 15% of missingness. The analysis with missing values performed best in recovering statistical estimates. The best strategy, when doing a Rasch analysis, is the analysis with missing values. If for some reason imputation is necessary, we recommend using the expectation-maximization algorithm.
In 2011 the Chinese leadership in rehabilitation, in collaboration with the International Classification of Functioning, Disability and Health (ICF) Research Branch, embarked on an effort towards the system-wide implementation of the ICF in the healthcare system in China. We report here on the lessons learned from the pilot phase of testing the ICF Generic Set, a parsimonious set of 7 ICF categories, which have been shown to best describe functioning across the general population and people with various health conditions, for use in routine clinical practice in China. The paper discusses whether classification and measurement are compatible, what number of ICF categories should be included in data collection in routine practice, and the usefulness of a functioning profile and functioning score in clinical practice and health research planning. In addition, the paper reflects on the use of ICF qualifiers in a rating scale and the particularities of certain ICF categories contained in the ICF Generic Set when used as items in the context of Chinese rehabilitation and healthcare. Finally, the steps required to enhance the utility of system-wide implementation of the ICF in rehabilitation and healthcare services are set out.
Objective: The aims of this study were to evaluate the feasibility of using the International Classification of Functioning, Disability and Health (ICF) Generic Set in routine clinical practice, and of creating a functioning score based on it, and, subsequently, to examine its sensitivity to change.
Methods: In this prospective cohort study, data from 761 adult inpatients from 21 Chinese hospitals were analysed. Each patient was assessed at admission and discharge. Feasibility was evaluated by analysing mean assessment time. The Rasch model was used to create a metric of functioning. Sensitivity to change was analysed with mixed-effects regression and by calculating standardized effect size based on Cohen's f2.
Results: Mean duration of assessment was 5.3 min, with a significant decrease between admission and discharge. After removal of the item remunerative employment, the remaining ICF Generic Set categories fitted the Rasch model well. With a mean improvement in functioning of 12.1 (95% confidence interval (95% CI): 11.5–12.6), this metric proved sensitive to change, both in terms of statistical significance (p < 0.001) and standardized effect size (Cohen's f2 = 2.35).
Discussion: The ICF Generic Set is feasible for use in routine clinical practice and is promising to serve as the basis for the development of a functioning score that is sensitive to change.
Background
Self-reported outcome instruments in health research have become increasingly important over the last decades. Occupational therapy interventions often focus on occupational balance. However, instruments to measure occupational balance are scarce. The aim of the study was therefore to develop a generic self-reported outcome instrument to assess occupational balance based on the experiences of patients and healthy people including an examination of its psychometric properties.
Methods
We conducted a qualitative analysis of the life stories of 90 people with and without chronic autoimmune diseases to identify components of occupational balance. Based on these components, the Occupational Balance-Questionnaire (OB-Quest) was developed. Construct validity and internal consistency of the OB-Quest were examined in quantitative data. We used Rasch analyses to determine overall fit of the items to the Rasch model, person separation index and potential differential item functioning. Dimensionality testing was conducted by the use of t-tests and Cronbach’s alpha.
Results
The following components emerged from the qualitative analyses: challenging and relaxing activities, activities with acknowledgement by the individual and by the sociocultural context, impact of health condition on activities, involvement in stressful activities and fewer stressing activities, rest and sleep, variety of activities, adaptation of activities according to changed living conditions and activities intended to care for oneself and for others. Based on these, the seven items of the questionnaire (OB-Quest) were developed. 251 people (132 with rheumatoid arthritis, 43 with systematic lupus erythematous and 76 healthy) filled in the OB-Quest. Dimensionality testing indicated multidimensionality of the questionnaire (t = 0.58, and 1.66 after item reduction, non-significant). The item on the component rest and sleep showed differential item functioning (health condition and age). Person separation index was 0.51. Cronbach’s alpha changed from 0.38 to 0.57 after deleting two items.
Conclusions
This questionnaire includes new items addressing components of occupational balance meaningful to patients and healthy people which have not been measured so far. The reduction of two items of the OB-Quest showed improved internal consistency. The multidimensionality of the questionnaire indicates the need for a summary of several components into subscales.
Objective: Functioning is an important outcome to measure in cohort studies. Clear and operational outcomes are needed to judge the quality of a cohort study. This paper outlines guiding principles for reporting functioning in cohort studies and addresses some outstanding issues.
Design: Principles of how to standardize reporting of data from a cohort study on functioning, by deriving scores that are most useful for further statistical analysis and reporting, are outlined. The Swiss Spinal Cord Injury Cohort Study Community Survey serves as a case in point to provide a practical application of these principles.
Methods and Results: Development of reporting scores must be conceptually coherent and metrically sound. The International Classification of Functioning, Disability and Health (ICF) can serve as the frame of reference for this, with its categories serving as reference units for reporting. To derive a score for further statistical analysis and reporting, items measuring a single latent trait must be invariant across groups. The Rasch measurement model is well suited to test these assumptions.
Conclusion: Our approach is a valuable guide for researchers and clinicians, as it fosters comparability of data, strengthens the comprehensiveness of scope, and provides invariant, interval-scaled data for further statistical analyses of functioning.