n. (in statistics) a relationship between two groups of observations indicating that the difference between them is unlikely to have occurred by chance alone. An assumption is made that there is no difference between the two populations from which the two groups come (null hypothesis). This is tested, and a calculation indicating that there is a probability of less than 5% (P value <0.05) that the difference observed occurred by chance is categorized as statistically significant and the null hypothesis is rejected. Some tests are parametric, based on the assumption that the range of observations are distributed by chance in a normal or Gaussian distribution, where 95% of observations lie within two standard deviations of the mean (Student’s t test to compare means). Nonparametric tests (Mann-Whitney U tests) make no assumptions about distribution patterns. See also frequency distribution, standard error.
Subjects: Medicine and Health.