Clinical Trials

❘❙❚■ GlossaryANOVA (analysis of variance)A statistical method for comparing several means by comparing variances. Itconcerns a normally distributed outcome (response) variable and a single categorical(predictor) variable representing treatments or groups. ANOVA is a special caseof a linear regression model by which group means can be easily compared.BiasSystematic errors associated with the inadequacies in the design, conduct,or analysis of a trial on the part of any of the participants of that trial (patients,medical personnel, trial coordinators, or researchers), or in publication of theresults, that make the estimate of a treatment effect deviate from its true value.Systematic errors are difficult to detect and cannot be analyzed statistically,but can be reduced by using randomization, treatment concealment, blinding,and standardized study procedures.Confidence intervalsA range of values within which the ‘true’ population parameter (eg, mean,proportion, treatment effect) is likely to lie. Usually 95% confidence intervals arequoted which implies there is 95% confidence in the statement that the ‘true’population parameter will lie somewhere between the lower and upper limits.ConfoundingA situation in which a variable (or factor) is related to both the study variable andthe outcome so that the effect of the study variable on the outcome is distorted.For example, if a study found that coffee consumption (study variable) isassociated with the risk of lung cancer (outcome), the confounding factor wouldbe cigarette smoking, since coffee drinking is often performed with the use ofcigarettes, which is the true risk factor for lung cancer. Thus we can say that theapparent association of coffee drinking with lung cancer is due to confounding bycigarette smoking (confounding factor). In clinical trials, confounding occurswhen a baseline characteristic (or variable) of patients is associated with theoutcome but unevenly distributed between treatment groups. As a result, theobserved treatment difference from the unadjusted (univariate) analysis can beexplained by the imbalanced distribution of this variable.454