Other impact numbers. Other impact number, absolute and relative impact numbers, used to assess the results of observational studies are reviewed.
NNT’s confidence interval. The calculation and interpretation of the confidence intervals of the number needed to treat are described, including the negative extremes of the interval.
Re-randomization in clinical trials. Re-randomization is the ability to randomize trial participants on more than one occasion, useful when large samples are required.
Random error and systematic error. We describe two types of errors, the random error due to measurement randomness and inaccuracies, and the systematic error or bias.
Hybrid designs The main observational hybrid designs are described: cohort nested cases and controls studies and cohort and case-control studies.