Imputation of missing values within WHODAS 2.0 data collected from low back pain patients using the response function approach.

To investigate the impact of missing data and imputation with the response function (RF) approach on bias and precision of disability estimates as well as reliability of scale of WHO Disability Assessment Schedule 2.0. Data were collected by face-to-face interviews and self-report surveys from 284 respondents with low back pain. Hypothetical datasets were created by using person and item parameters of real data. A simulation study was devised to assess the ability parameters and reliability measures on incomplete and imputed datasets. Rasch model was used to evaluate latent trait levels. Imputation was carried out using the response function method. Almost the same level of bias and MSE was reached. While the missing rate increases, the Person separation index slightly reduced, still exceeded 0.94 and Cronbach alpha values have similar mean values of 0.99 with larger variations. After deletion of four items of "work or school activities" in domain 5, reliability measures reduced the lowest. Construct validity is preserved. Problems regarding the compliance of the items with the target group still persist. When researchers encounter missingness in data collected with WHODAS 2.0, the response function can be usefully implemented to impute missing values to improve the reliability of disability level estimates. The Turkish version of the 36-item WHODAS is reliable and valid for assessing health and disability status in patients with low back pain. A critical issue is a systematic nonresponse was highly observed in items related to "work/school life activities" which are allowed to be skipped and excluded from the scoring according to WHODAS 2.0 training manual. Imputation of missing values within four items of "work or school activities" in domain 5 using the response function approach showed satisfactory reliability for the estimation of disability in adults with low back pain. This study showed missing data imputations with response function can be implemented by a statistician as contribute to a missing data management process better tailored to clinicians' interpretations. [ABSTRACT FROM AUTHOR]