Rater bias in a blinded randomized placebo-controlled psychiatry trial.

Rater bias occurs when rater knowledge of treatment assignment modifies the outcome assessment. Raters may be unconsciously influenced by inclinations for or against a particular treatment and consequently may give a more or less generous assessment depending upon these biases. Blinding of raters by keeping raters unaware of treatment assignment is one way to limit bias influencing assessment due to knowledge of treatment assignment. Unblinding may be particularly problematic in efficacy studies comparing placebo to drugs and/or non-drug psychotherapy treatments where subjects may reveal drug side-effects or mention their therapist by name, thus unblinding their treatment assignment. We present a new instrumental variable statistical approach for assessing the association between success in blinding and its impact on efficacy estimates of active drug and/or cognitive behavioural psychotherapy versus placebo in the multicentre comparative treatment study of panic disorder. Despite the uncertainty involved in assessing bias that may be unobserved and unconscious, we will show how to derive a bound for the impact of rater bias.