Significance Tests
When two quantities are statistically independent, the distribution of is not easily characterizable in terms of known distributions. However, for the following statistic, is approximately distributed as a standard normal when the variables are statistically independent:
Thus, to test whether two variables are statistically dependent, one computes, and finds the cumulative probability for a standard normal distribution at . For a 2-tailed test, multiply that number by two to obtain the p-value. If the p-value is below a given significance level, one rejects the null hypothesis (at that significance level) that the quantities are statistically independent.
Numerous adjustments should be added to when accounting for ties. The following statistic, has the same distribution as the distribution, and is again approximately equal to a standard normal distribution when the quantities are statistically independent:
where
Read more about this topic: Kendall Tau Rank Correlation Coefficient
Famous quotes containing the words significance and/or tests:
“For a parent, its hard to recognize the significance of your work when youre immersed in the mundane details. Few of us, as we run the bath water or spread the peanut butter on the bread, proclaim proudly, Im making my contribution to the future of the planet. But with the exception of global hunger, few jobs in the world of paychecks and promotions compare in significance to the job of parent.”
—Joyce Maynard (20th century)
“From a hasty glance through the various tests I figure it out that I would be classified in Group B, indicating Low Average Ability, reserved usually for those just learning to speak the English Language and preparing for a career of holding a spike while another man hits it.”
—Robert Benchley (18891945)
