SOURCES OF ERROR IN CHART REVIEWS AND THEIR SOLUTIONSįrom Kaji et al (2014) and Gilbert et al (1996):
#Retrospective analysis software#
More than one confounder is controlled simultaneously, if a larger number of confounders needs to be adjusted for computer software and statistical advice is necessary.Used if only a few confounders exist and if the size of one of the comparison groups is much larger than the other.Find pairs of patients that have specific characteristics in common, but received different treatments compares outcome only in these pairs.Used if only one key confounding variable exists.Divide all patients into subgroups according to a risk factor, then perform comparison within these subgroups.Used if treatment and control group are selected by a chance mechanism.
Retrospective studies are designed to analyse pre-existing data, and are subject to numerous biases as a result.