Statistical issues in quality-of-life assessment

In recent years, the assessment of drug effects on quality of life (QOL) has become very popular in clinical trials. QOL assessment quantifies the ability of a person to function normally in society. It may be used to distinguish between therapies that appear to be equally efficacious and equally safe. QOL is usually assessed by a QOL instrument, which consists of a number of questions. A QOL instrument is a very subjective tool that usually has a large variation. To ensure the accuracy and reliability of QOL assessment in clinical trials, the adopted QOL instrument should be validated. Some statistical tests are proposed for validation of a QOL instrument in terms of validity, reliability, test-retest reproducibility, responsiveness, and sensitivity. Some statistical issues regarding the validation of utility analysis and calibration for QOL against life events and/or disease status will also be discussed.