J. Bernhard et al., MISSING QUALITY-OF-LIFE DATA IN CANCER CLINICAL-TRIALS - SERIOUS PROBLEMS AND CHALLENGES, Statistics in medicine, 17(5-7), 1998, pp. 517-532
Measurement of quality of life (QOL) in cancer clinical trials has inc
reased in recent years as more groups realize the importance of such e
ndpoints. A key problem has been missing data, Some QOL data may unavo
idably be missing, as for example when patients are too ill to complet
e forms. Other important sources are potentially avoidable and can bro
adly be divided into three categories: (i) methodological factors; (ii
) logistic and administrative factors; (iii) patient-related factors,
Logistic and administrative factors, for example, staff oversights, ha
ve proven to be most important, Since most QOL measurements require pa
tient self-report, it is usually not possible to rectify the failure t
o collect baseline data or any follow-up assessments. There is strong
evidence that such data are not 'missing at random', and cannot be ign
ored without introducing bias, Although several approaches to the anal
ysis of partly missing data have been described, none is entirely sati
sfactory, Prevention of avoidable missing data is better than attempte
d cure. In July 1996, an international conference on missing QOL data
in cancer clinical trials reported the experience of most major groups
involved, This paper will serve as an introduction to the problem and
provide an estimation of its magnitude, and approaches to its prevent
ion and solution. (C) 1998 John Wiley & Sons, Ltd.