Why internal and external validity of experimental studies are relevant for clinical practice?

Abstract

In randomised controlled trials (RCTs) there are two types of validity: internal validity and external validity. Internal validity refers to the extent to which the observed difference between groups can be correctly attributed to the intervention under investigation. In other words, it is the extent to which the design and conduct of the trial eliminate error. Internal validity might be threatened by two types of errors: systematic error (also called bias) and chance error (also called random error or statistical error) (Keirse & Hanssens, 2000. Systematic error, or bias, may be the consequence of erroneous ways of collecting, analysing and interpreting data. This may produce differences between treatments that are not real, with an overestimation or an underestimation of the true beneficial or harmful effect of an intervention (Juni et al., 2001). In RCTs there are four types of bias: selection bias (when the groups differ in baseline characteristics because of the way participants are selected), performance bias (when the care provided to the trial participants differs systematically between the experimental and control group), detection bias (when there are systematic differences in outcome assessment), and attrition bias (when the loss of participants from the study systematically differs between the experimental and control group). By contrast, chance error, or statistical error, is due to outcome variability that may arise by chance alone. Studies with small sample sizes are more likely to incur in this type of error than studies with large sample sizes. Thus, the risk of random error may be minimised by recruiting sufficiently large samples of patients.