Abstract
This paper describes the methods appropriate for calculating sample sizes for clinical trials assessing quality of life (QOL). An example from a randomized trial of patients with small cell lung cancer completing the Hospital Anxiety and Depression Scale (HADS) is used for illustration. Sample size estimates calculated assuming that the data are either of the Normal form or binary are compared to estimates derived using an ordered categorical approach. In our example, since the data are very skewed, the Normal and binary approaches are shown to be unsatisfactory: binary methods may lead to substantial over estimates of sample size and Normal methods take no account of the asymmetric nature of the distribution. When summarizing normative data for QOL scores the frequency distributions should always be given so that one can assess if non-parametric methods should be used for sample size calculations and analysis. Further work is needed to discover what changes in QOL scores represent clinical importance for health technology interventions.
Similar content being viewed by others
References
Fayers P, Machin D. Sample size: how many patients are necessary? Br J Cancer 1995; 72: 1-9.
Burnard B, Kernan WN, Feinstein AR. Indexes and boundaries for ‘quantitative significance’ in statistical decisions. JClin Epidemiol 1990; 43: 1273-1284.
CPMP Working Party on Efficacy of Medicinal Products. Biostatisticalmethodology in clinical trials in applications formarketing authorizations formedicinal products. Stats Med 1995; 14: 1659-1682.
British Medical Journal. Instructions to authors. Br Med J 1995; 310: 50-53.
Staquet MJ, Berzon R, Osoba D, Machin D. Guidelines for reporting results of quality of life assessments in clinical trials. Qual Life Res (in press)
Altman DG, Bland JM. Absence of evidence is not evidence of absence. Br Med J 1995; 311: 485.
Machin D, Campbell MJ, Fayers PM, Pinol AY. Sample Size Tables for Clinical Studies.Oxford, UK: Blackwell Scientific [In press].
Medical Research Council Lung CancerWorking Party. A randomised trial of three or six courses of etoposide cyclophosphamide methotrexate and vincristine or six courses of etoposide and ifosfamide in small cell lung cancer (SCLC) II: quality of life. Br J Cancer 1993; 68: 1157-1166.
Hopwood P, Stephens RJ, Machin D. Approaches to the analysis of quality of life data: experiences gained from a Medical Research Council Lung Cancer Working Party palliative chemotherapy trial. Qual Life Res 1994; 3: 339-351.
Juniper EJ, Guyatt GH, Willan A, Griffith LE. Determining a minimal important change in a disease specific quality of life questionnaire. J Clin Epidemiol 1994; 47: 81-87.
Julious SA, George S, Campbell MJ. Sample sizes for studies with SF-36. J Epidemiol Comm Health 1995; 49: 642-644.
Whitehead J. Sample size calculations for ordered categorical data. Stats Med 1993; 12: 2257-2272.
Zigmond AS, Snaith RP. The Hospital Anxiety and Depression Scale. Acta Psychol Scand 1983; 67: 361-370.
Boskey CM, Fosbury JA, Cochrane GM. The psychological factors associated with poor compliance with treatment in asthma. Euro Respir J 1995; 8: 899- 904.
Ware JE, Snow KK, Kosinski M, Gandek B. SF-36 Health SurveyManual and InterpretationGuide.Boston, MA(USA): New England Medical Centre, The Health Institute, 1993.
Ware JE, Brook RH, Williams KN, Stewart AL and Davies-Avery A. Conceptualization and Measurement of Health for Adults in the Health Insurance Study. Vol. 1 Model of Health and Methodology.Santa Monica, CA (USA): Rand Corporation, 1980. (Publication No R-1 987/1-HEW.)
Jenkinson C, Coulter A, Wright L. Short form 36 (SF-36) health survey questionnaire: normative data for adults of working age. Br Med J 1993; 306: 1437-1440.
Campbell MJ, Julious S, Altman DG. Sample sizes for binary, ordered categorical and continuous outcomes in two group comparisons. Br Med J 1995; 311: 1145-1148.
Medical Research Council Lung Cancer Working Party. A randomised trial of etoposide cyclophosphamide methotrexate and vincristine versus etoposide and vincristine in the palliative treatment of patients with small cell lung cancer (SCLC) and poor prognosis. Br J Cancer 1996; 73: 404-413.
Campbell MJ, Machin D. Medical Statistics: A Common Sense Approach. Second Edition.Chichester, UK: JohnWiley, 1993.
Julious SA, Campbell MJ. Sample size calculations for ordered categorical data. Stats Med 1996; 15: 1065-1066.
Conover WJ. Practical Nonparametric Statistics. Second Edition. New York, NY (USA): John Wiley, 1980.
Cohen J. Statistical Power Analysis for the Behavioral Sciences. Second Edition. NJ (USA): Lawrence Earlbaum, 1988.
Parmar MKB, Spiegelhalter DJ, Freedman LS and the CHART Steering Committee. The CHART trials: Bayesian design and monitoring in practice. Stats Med 1995; 13: 1297-1312.
Birkett MA, Day SJ. Internal pilot studies for estimating sample size. Stats Med 1994; 13: 2455-2463.
Keen ON. The log transformation is special. Stats Med 1995; 14: 811-819.
Bland JM, Altman DG. Logarithms. Br Med J 1996; 312: 700.
SAS. Cary, NC (USA): SAS Institute Inc., 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Julious, S.A., George, S., Machin, D. et al. Sample sizes for randomized trials measuring quality of life in cancer patients. Qual Life Res 6, 109–117 (1997). https://doi.org/10.1023/A:1026481815304
Published:
Issue Date:
DOI: https://doi.org/10.1023/A:1026481815304