Missing data methods for dealing with missing items in quality of life questionnaires. A comparison by simulation of personal mean score, full information maximum likelihood, multiple imputation, and hot deck techniques applied to the SF-36 in the French 2003 decennial health survey

Peyre, Hugo; Leplège, Alain; Coste, Joël

doi:10.1007/s11136-010-9740-3

Cited by 212 publications

(122 citation statements)

References 31 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Applying the interview version of a questionnaire instead of postal self-administration can improve response rates and reduce missing data [41]. In addition, methods to handle missing data, such as multiple imputation techniques, were recommended in order to quantify potential biases [41,47]. In terms of the analysis of psychometric properties we showed that the 12-item WHODAS 2.0 fulfilled the assumptions of Rasch modeling.…”

Section: Discussionmentioning

confidence: 89%

Feasibility and psychometric properties of the German 12-item WHO Disability Assessment Schedule (WHODAS 2.0) in a population-based sample of patients with myocardial infarction from the MONICA/KORA myocardial infarction registry

Kirchberger

Braitmayer

Coenen

et al. 2014

Popul Health Metrics

View full text Add to dashboard Cite

Background: The World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0) provides a standardized assessment of functioning and disability in individuals with any kind of disease. So far, data on feasibility and psychometric properties of the 12-item WHODAS 2.0 in patients with acute myocardial infarction (AMI) are not available. Thus, the objective of this study was to investigate feasibility and psychometric properties of this questionnaire in a population-based sample of persons with AMI. Methods: The sample consisted of 2077 persons (age 35-85 years) with AMI from the population-based MONICA/KORA Myocardial Infarction Registry, Augsburg, Germany, who responded to a postal follow-up survey in 2011. Feasibility was assessed by the number of missing WHODAS 2.0 items and analyzed using multivariate logistic regression modeling. Psychometric properties were determined using Rasch analysis. It included testing of unidimensionality, monotonicity and local independency, Partial Credit Model (PCM) fitting, and testing for Differential Item Functioning (DIF). Concurrent validity was tested by a linear additive model predicting the WHODAS disability score based on a number of independent variables.

show abstract

Section: Discussionmentioning

confidence: 89%

Feasibility and psychometric properties of the German 12-item WHO Disability Assessment Schedule (WHODAS 2.0) in a population-based sample of patients with myocardial infarction from the MONICA/KORA myocardial infarction registry

Kirchberger

Braitmayer

Coenen

et al. 2014

Popul Health Metrics

View full text Add to dashboard Cite

show abstract

“…Unfortunately, there is no way to determine whether data are NMAR because the information required to make this determination is missing (Allison 2012). Research indicates that MI, FIML, and EM are significantly less likely to lead to bias than traditional approaches to handling missing data at all three levels of missingness (Peyre et al 2011). Consequently, the current analyses were based on the assumption that data were missing at random.…”

Section: Missing Datamentioning

confidence: 99%

Breaking the cycle demonstration project: using a quasi-experimental analysis to test the “worst of both worlds” hypothesis and risk principle

Walters

2015

J Exp Criminol

View full text Add to dashboard Cite

Objectives The purpose of this study was to test the Bworst of both worlds^hypothesis and the risk principle in a sample of drug-involved offenders enrolled in the Breaking the Cycle (BTC) demonstration project, an intensive drug intervention implemented in Birmingham, Alabama, Jacksonville, Florida, and Tacoma, Washington. Methods A group of 1081 drug-involved offenders enrolled in BTC were compared to 934 drug-involved offenders (pre-BTC) who processed through the regular court system of each city 1 year prior to implementation of BTC. Participants from both groups were divided into risk levels based on scores from the Addiction Severity Index (ASI) Drug (D) and Legal (L) scales. Individuals who scored at or above the mean on both the ASI-D and ASI-L were identified as high risk, individuals who scored at or above the mean on either the ASI-D or ASI-L but not both were identified as moderate risk, and individuals who scored below the mean on both the ASI-D and ASI-L were identified as low risk. Results Consistent with the risk principle, high-risk BTC participants displayed significant improvements in subsequent drug problem days, criminal offending, and days spent in jail relative to high-risk pre-BTC participants. There was no apparent benefit of BTC enrollment for moderate-and low-risk participants. Conclusions These results indicate that drug-crime comorbidity can be used to assess risk and that individuals identified as high risk are more likely to benefit from higherintensity forms of intervention than moderate-or low-risk individuals.

show abstract

“…Missing data of the SF-36 were computed per subscale by imputation of personal mean scores, in case half or less of questions within the subscale were missing (24). Imputation of personal mean scores per subscale was also used if one item or less was missing per subscale in the HADS and MFI-20.…”

Section: Missing Datamentioning

confidence: 99%

Quality of life is decreased in patients with paragangliomas

Hulsteijn

Louisse

Havekes

et al. 2013

European Journal of Endocrinology

View full text Add to dashboard Cite

Context: Germline mutations in succinate dehydrogenase (SDH) genes predispose carriers for developing paragangliomas, and studies on their quality of life (QoL) are scarce. Objectives: The objectives of this study were to assess QoL in patients with paragangliomas (PGL), to evaluate long-term QoL, and to explore potential differences in QoL between SDH mutation carriers and paraganglioma patients without an SDH mutation. Design: Cross-sectional, case-control study. Setting: Tertiary referral center. Subjects: One hundred and seventy four paraganglioma patients were included: 25 SDHB, two SDHC, and 122 SDHD mutation carriers and 25 patients without an SDH mutation. They provided 100 peers as control persons. Furthermore, patients were compared with age-adjusted reference populations. Main outcome measures: QoL was assessed using three validated health-related QoL questionnaires: the Hospital Anxiety and Depression Scale, the Multidimensional Fatigue Index 20, and the Short Form 36. Results: Patients reported a significantly impaired QoL compared with their own controls, mainly on fatigue and physical condition subscales. Compared with age-adjusted literature values, patients had significantly impaired scores on physical, psychological, and social subscales. A decreased QoL was mainly related to paraganglioma-associated complaints.There was no difference in QoL between the various SDH mutation carriers or paraganglioma patients without an SDH mutation. QoL in asymptomatic mutation carriers, i.e. without manifest disease, did not differ from QoL of the general population. Long-term results in 41 patients showed no alteration in QoL besides a reduced level of activity. Conclusion: QoL is decreased in paraganglioma patients but stable when measured over time.

show abstract

Missing data methods for dealing with missing items in quality of life questionnaires. A comparison by simulation of personal mean score, full information maximum likelihood, multiple imputation, and hot deck techniques applied to the SF-36 in the French 2003 decennial health survey

Cited by 212 publications

References 31 publications

Feasibility and psychometric properties of the German 12-item WHO Disability Assessment Schedule (WHODAS 2.0) in a population-based sample of patients with myocardial infarction from the MONICA/KORA myocardial infarction registry

Feasibility and psychometric properties of the German 12-item WHO Disability Assessment Schedule (WHODAS 2.0) in a population-based sample of patients with myocardial infarction from the MONICA/KORA myocardial infarction registry

Breaking the cycle demonstration project: using a quasi-experimental analysis to test the “worst of both worlds” hypothesis and risk principle

Quality of life is decreased in patients with paragangliomas

Contact Info

Product

Resources

About