Dataset Information

The use of bootstrap methods for analysing Health-Related Quality of Life outcomes (particularly the SF-36).

ABSTRACT: Health-Related Quality of Life (HRQoL) measures are becoming increasingly used in clinical trials as primary outcome measures. Investigators are now asking statisticians for advice on how to analyse studies that have used HRQoL outcomes.HRQoL outcomes, like the SF-36, are usually measured on an ordinal scale. However, most investigators assume that there exists an underlying continuous latent variable that measures HRQoL, and that the actual measured outcomes (the ordered categories), reflect contiguous intervals along this continuum. The ordinal scaling of HRQoL measures means they tend to generate data that have discrete, bounded and skewed distributions. Thus, standard methods of analysis such as the t-test and linear regression that assume Normality and constant variance may not be appropriate. For this reason, conventional statistical advice would suggest that non-parametric methods be used to analyse HRQoL data. The bootstrap is one such computer intensive non-parametric method for analysing data. We used the bootstrap for hypothesis testing and the estimation of standard errors and confidence intervals for parameters, in four datasets (which illustrate the different aspects of study design). We then compared and contrasted the bootstrap with standard methods of analysing HRQoL outcomes. The standard methods included t-tests, linear regression, summary measures and General Linear Models.Overall, in the datasets we studied, using the SF-36 outcome, bootstrap methods produce results similar to conventional statistical methods. This is likely because the t-test and linear regression are robust to the violations of assumptions that HRQoL data are likely to cause (i.e. non-Normality). While particular to our datasets, these findings are likely to generalise to other HRQoL outcomes, which have discrete, bounded and skewed distributions. Future research with other HRQoL outcome measures, interventions and populations, is required to confirm this conclusion.

SUBMITTER: Walters SJ

PROVIDER: S-EPMC543443 | biostudies-literature | 2004 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The use of bootstrap methods for analysing Health-Related Quality of Life outcomes (particularly the SF-36).

Walters Stephen J SJ Campbell Michael J MJ

Health and quality of life outcomes 20041209

Health-Related Quality of Life (HRQoL) measures are becoming increasingly used in clinical trials as primary outcome measures. Investigators are now asking statisticians for advice on how to analyse studies that have used HRQoL outcomes.HRQoL outcomes, like the SF-36, are usually measured on an ordinal scale. However, most investigators assume that there exists an underlying continuous latent variable that measures HRQoL, and that the actual measured outcomes (the ordered categories), reflect co ...[more]

PMID: 15588308

Similar Datasets

Project description:BackgroundHealth-related quality of life (HRQOL) has a direct association with increased morbidity and mortality among end stage renal disease patients. Valid and reliable instruments to measure the HRQOL of patients with end stage renal disease are therefore required. This study aimed to translate, culturally adapt and evaluate the psychometric properties of the Amharic version of the Kidney Disease Quality of Life-36 (KDQOL-36) instrument in Ethiopian patients with end stage renal disease undergoing hemodialysis.MethodsThe KDQOL-36 instrument was developed for individuals with kidney disease who are being treated with dialysis and includes both generic and disease-specific components. The KDQOL-36 was translated to Amharic language and distributed to a cross-sectional sample of 292 hemodialysis patients. The psychometric evaluation included construct validity through corrected item-total correlation, confirmatory factor analysis and known group analysis. Convergent validity was evaluated by correlations between each of the three kidney disease targeted scales (symptoms/problems list, burden of kidney disease and effects of kidney diseases) and the European Quality of Life 5D-5L and Visual Analog Scales. Regarding reliability, internal consistency and test-retest reliability were assessed.ResultsTwo hundred ninety-two patients with a mean age of 48 (SD ± 14.7) completed the questionnaire. Corrected item- total correlation scores were > 0.4 for all items. Confirmatory factor analysis revealed a two χ2 /df was 4.4, Root Mean Square Error of Approximation (RMSEA) = 0.108 (90% CI 0.064-0.095), Comparative Fit Index (CFI) = 0.922, Tucker Lewis Index (TLI) = 0.948 and Standardized Root mean-squared residual (SRMR) = 0.058) and three χ2 /df = 3.1, RMSEA = 0.085 (90% CI 0.064-0.095), CFI = 0.854, TLI = 0.838 and SRMR = 0.067) factor models for the generic and disease specific components respectively. The mean scores of the three kidney disease targeted domains were correlated to the EQ-5D-5L & VAS with correlation coefficients of large magnitude (0.55-0.81). The reliability of the instrument was satisfactory (Cronbach's alpha = 0.81-0.91) and Intra-class correlation (ICC) = 0.90-0.96).ConclusionThe Amharic version of the KDQOL-36 is a reliable and valid instrument recommended for assessment of HRQOL of Ethiopian patients on hemodialysis.

Dataset Information

The use of bootstrap methods for analysing Health-Related Quality of Life outcomes (particularly the SF-36).

Publications

The use of bootstrap methods for analysing Health-Related Quality of Life outcomes (particularly the SF-36).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets