2019, Number 4
Clinical versus statistical significance
Moragrega AJL
Full text
Language: English
References: 2
Page: 147-149
PDF size: 159.87 Kb.
Text Extraction
Statistical significance refers to the likelihood that a relationship between two or more variables, is caused by something other than chance.1 Statistical hypothesis testing is used to determine whether the result of a data set is statistically significant. In medicine usually it is used for the comparison of some characteristics of two groups. Two examples are patient’s age or weight previous to the intervention or glucose levels with the administration of two different drugs. Since in medicine we always work with samples and never with a whole population, we make inferences from the sample to estimate with the statistics the parameter whose values we really do not know (Figure 1). Then we use the knowledge derived from taking many samples from a population, distributing them (central limit theorem and the standard error of the mean), knowing the properties of the distribution (e.g. normal or Gaussian curve) and finally calculating the probability that the sample means difference is due to chance or shows a true difference present in the universe (p value). There is a risk to be wrong if we accept the difference as being true when in fact it does not exist (type I or alfa), and also a risk to accept the null hypothesis of no difference when in fact it does exist (type II or beta).REFERENCES