Dl. Fairclough et al., WHY ARE MISSING QUALITY-OF-LIFE DATA A PROBLEM IN CLINICAL-TRIALS OF CANCER-THERAPY, Statistics in medicine, 17(5-7), 1998, pp. 667-677
Assessment of health related quality of life has become an important e
ndpoint in many cancer clinical trials. Because the participants of th
ese trials often experience disease and treatment related morbidity an
d mortality, non-random missing assessments are inevitable. Examples a
re presented from several such trials that illustrate the impact of mi
ssing data on the analysis of QOL in these trials, The sensitivity of
different analyses depends on the proportion of assessments that are m
issing and the strength of the association of the underlying reasons f
or missing data with disease and treatment related morbidity and morta
lity. In the setting of clinical trials of cancer therapy, the assumpt
ion that the data are missing completely at random (MCAR) and analyses
of complete cases is usually unjustified. Further, the assumption of
missing at random (MAR) may also be violated in many trials and models
appropriate for non-ignorable missing data should be explored. Recomm
endations are presented to minimize missing data, to obtain useful doc
umentation concerning the reasons for missing data and to perform sens
itivity analyses. (C) 1998 John Wiley & Sons, Ltd.