P-values & Statistical Significance

This lesson is part of Premium

Definition: probability of observing results as extreme as these IF the null were true. p<0.05 conventionally 'significant'. What p does NOT tell you (effect size, clinical importance, probability H0 is true). Statistical vs clinical significance. Multiple testing inflates false positives (Bonferroni idea). PValueDemo. Exam tip: a tiny p with a trivial effect size can be clinically meaningless; large trials make trivial differences 'significant'.

Premium unlocks all 40 lessons, every calculator and the timed mock.