Concepts Of Bias And Statistical Necessities

Bias is a general consideration in clinical trial design, regardless of the type of trial being conducted. It is considered here as an overarching issue, to be applied to the systematic description of the types of study design, as considered below.

The word 'bias' has many definitions, but in this context it is best described as a distortion of, or prejudice towards, observed effects that may or may not truly be due to the action of the test drug(s). Many things can distort the true measurement of drug action, and bias is the trialist's most unremitting enemy, which comes from many quarters (Table 11.1). The clinical trialist must be sufficiently humble to realize that he/she, him/herself, may be a source of bias.

The pharmaceutical physician may not be expected to be a specialist statistician, and statistics are not the subject of this chapter. However, the ability to talk to and understand statisticians is absolutely essential (sine qua non: involve a good statistician from the moment a clinical trial is contemplated). Furthermore, the pharmaceutical physician should be confident of a sound understanding of the concepts of type I and type II error, and the probabilities a and p (e.g. Freiman et al.

• Poorly matched placebos

• Subtle or obvious non-randomization of patients

• Failure of double-blinding, e.g. when pharmacodynamic effects cannot be controlled

• Prompting of prejudiced subjective responses

• Non-uniform medical monitoring

• Protocol amendments with unequal effects on treatment groups

• Peculiarities of the study site itself (e.g. psychotropic drug effects in psychiatric institutions which fail to predict effects in outpatients)

• Differing medical definitions across languages, dialects or countries (e.g. 'mania')

• CRF with leading questions, either toward or away from adverse event reporting

• Informal, 'break the blind' games played at study sites

• Selective rigour in collection and storage of biological samples

• Selectively incomplete data sets for each patient

• Inappropriate use of parametric or non-parametric statistical techniques

• Failure to adequately define end-points prospectively, and retrospective 'data dredging'

• Acceptance of correlation as evidence of causation

• Averaging of proportionate responses from non-homogenous treatment groups, also known as Simpson's paradox; see Spilker (1991)

• Unsceptically accepting anecdotal reports

• Tendency to publish only positive results

CRF case report form; the term 'controlled' is used in its technical sense (see section on Bias and Statistical Necessities, this chapter).

1978). This is one of your best defences against bias.

0 0

Post a comment