Hugo Peyre1, Alain Leplège, Joël Coste. 1. Biostatistics and Epidemiology Unit, Assistance Publique-Hôpitaux de Paris, Hôpital Cochin, Nancy-Université, Université Paris-Descartes, Paris Cedex 14, France.
Abstract
PURPOSE: Missing items are common in quality of life (QoL) questionnaires and present a challenge for research in this field. It remains unclear which of the various methods proposed to deal with missing data performs best in this context. We compared personal mean score, full information maximum likelihood, multiple imputation, and hot deck techniques using various realistic simulation scenarios of item missingness in QoL questionnaires constructed within the framework of classical test theory. METHODS: Samples of 300 and 1,000 subjects were randomly drawn from the 2003 INSEE Decennial Health Survey (of 23,018 subjects representative of the French population and having completed the SF-36) and various patterns of missing data were generated according to three different item non-response rates (3, 6, and 9%) and three types of missing data (Little and Rubin's "missing completely at random," "missing at random," and "missing not at random"). The missing data methods were evaluated in terms of accuracy and precision for the analysis of one descriptive and one association parameter for three different scales of the SF-36. RESULTS: For all item non-response rates and types of missing data, multiple imputation and full information maximum likelihood appeared superior to the personal mean score and especially to hot deck in terms of accuracy and precision; however, the use of personal mean score was associated with insignificant bias (relative bias <2%) in all studied situations. CONCLUSIONS: Whereas multiple imputation and full information maximum likelihood are confirmed as reference methods, the personal mean score appears nonetheless appropriate for dealing with items missing from completed SF-36 questionnaires in most situations of routine use. These results can reasonably be extended to other questionnaires constructed according to classical test theory.
PURPOSE: Missing items are common in quality of life (QoL) questionnaires and present a challenge for research in this field. It remains unclear which of the various methods proposed to deal with missing data performs best in this context. We compared personal mean score, full information maximum likelihood, multiple imputation, and hot deck techniques using various realistic simulation scenarios of item missingness in QoL questionnaires constructed within the framework of classical test theory. METHODS: Samples of 300 and 1,000 subjects were randomly drawn from the 2003 INSEE Decennial Health Survey (of 23,018 subjects representative of the French population and having completed the SF-36) and various patterns of missing data were generated according to three different item non-response rates (3, 6, and 9%) and three types of missing data (Little and Rubin's "missing completely at random," "missing at random," and "missing not at random"). The missing data methods were evaluated in terms of accuracy and precision for the analysis of one descriptive and one association parameter for three different scales of the SF-36. RESULTS: For all item non-response rates and types of missing data, multiple imputation and full information maximum likelihood appeared superior to the personal mean score and especially to hot deck in terms of accuracy and precision; however, the use of personal mean score was associated with insignificant bias (relative bias <2%) in all studied situations. CONCLUSIONS: Whereas multiple imputation and full information maximum likelihood are confirmed as reference methods, the personal mean score appears nonetheless appropriate for dealing with items missing from completed SF-36 questionnaires in most situations of routine use. These results can reasonably be extended to other questionnaires constructed according to classical test theory.
Authors: Tony W C Mak; Wing Wa Leung; Dennis K Y Ngo; Janet F Y Lee; Sophie S F Hon; Simon S M Ng Journal: Int J Colorectal Dis Date: 2015-12-10 Impact factor: 2.571
Authors: Élodie de Bock; Jean-Benoit Hardouin; Myriam Blanchin; Tanguy Le Neel; Gildas Kubis; Véronique Sébille Journal: Qual Life Res Date: 2014-02-23 Impact factor: 4.147
Authors: Pierre Michel; Karine Baumstarck; Christophe Lancon; Badih Ghattas; Anderson Loundou; Pascal Auquier; Laurent Boyer Journal: Qual Life Res Date: 2017-03-25 Impact factor: 4.147
Authors: Johan S Bundgaard; Lauge Østergaard; Gunnar Gislason; Jens J Thune; Jens C Nielsen; Jens Haarbo; Lars Videbæk; Line L Olesen; Anna M Thøgersen; Christian Torp-Pedersen; Susanne S Pedersen; Lars Køber; Ulrik M Mogensen Journal: Qual Life Res Date: 2019-07-10 Impact factor: 4.147
Authors: Lisa Shaw; Nawaraj Bhattarai; Robin Cant; Avril Drummond; Gary A Ford; Anne Forster; Richard Francis; Katie Hills; Denise Howel; Anne Marie Laverty; Christopher McKevitt; Peter McMeekin; Christopher Price; Elaine Stamp; Eleanor Stevens; Luke Vale; Helen Rodgers Journal: Health Technol Assess Date: 2020-05 Impact factor: 4.014