PSC 165 Lecture Notes - Lecture 1: Karl Popper, Thomas Kuhn, Null Hypothesis
Document Summary
P = probability that you would get the effect you did even if the hypothesis were not true. Often set at . 05 (meaning a 5% chance of a type 1 error) Power = likelihood of observing a statistically significant effect. Often (should be) estimated prior to study to determine sample size. Usually 80% considered adequate, meaning 80% likely to observe a. Significant effect (e. g. , at p < . 05) if there really is an effect in nature. Power of test (sample size, measurement reliability) Study: randomized controlled trial with one group who gets ssris and another who gets placebo; the ssri group gets better (d = . 30) What is the probability that you would observe an effect of d = . 30 if. Medication is the most effective treatment for depression and anxiety. Psychotherapy is the most effective treatment for depression & anxiety.
