QMS 202 Study Guide - Midterm Guide: Mann–Whitney U Test, Repeated Measures Design, Correlation Ratio
21 Jun 2017
School
Department
Course
Professor
Document Summary
Answer to a research question or assumption made about a population parameter (not sample estimate!) Alternative hypothesis (h1) research/experimental hypothesis: choose alpha signi cance level (. 05) It"s the area for which extreme score are unlikely to occur if the null hypothesis is true: compute the appropriate test statistic, make the decision. If value is greater than or equal to, reject h0. Did reject h0 implies an acceptance of h1: conclusion. If reject = there is a statistically signi cant. Calculate effect size: a measure of the magnitude of a treatment effect. Type 1: reject h0 while it"s true false + relate to alpha. Type 2: retain h1 while it"s false false relate to beta (control with sample size, an increase means less error) Requirements population is normally distributed population standard deviation must be known must be a random sample. Calculate the z score of your sample mean. Transform normal distribution in a standard normal distribution.
