Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Just a note

In this situation we have used θ rather than because the latter would suggest your observed value of that statistic is an estimate of a population parameter, Θ, which would imply your observations are a random sample of some wider population.

Whilst that may sometimes be true, the permutation test model explicitly ignores any variation such a random selection would introduce. In other words a permutation test's outcome is 'conditional' upon, and specific to, a given set of observations.

Nevertheless, whilst the reasoning of permutation tests cannot be extended to a more general 'parent' population, confidence limits should inform us about tests of θ given a range of hypotheses, in which case you will need to modify your observations accordingly.