The ______ ______ separates the whole number part from the decimal part of a mixed

Week 11: Hypothesis Testing 16 November 2016 Basic Statistics for Research Professor HK Dong Wendy Liu Logic of Hypothesis Testing 1. State the hypothesis 2. Define the decision method 3. Gather data 4. Make a decision Rare event rule of inferential statistics – if, under a given assumption, the probability of a particular observed event is exceptionally small (set by α), we conclude the assumption is probably not correct H 0 Null Hypothesis – assume null hypothesis is true  What is tested  Has serious outcome if incorrect decision is made  Always has equality sign: =, ≥, ≤  Designated H 0  Specified as o H 0 µ = # o H 0 µ ≥ # o H 0 µ ≤ # H a Alternative Hypothesis – true if H0is false  Opposite of null hypothesis  Hypothesis that will be accepted only if the data provide convincing evidence of its truth  Designated H a  Stated as o H a µ ≠ #  Two-tailed test o H a µ > #  Upper/right-tailed test o H a µ < #  Lower/left-tailed test Level of significance (α)  Probability  Defines unlikely values of sample statistic if null hypothesis is true o Rejection region of sampling distribution data  Typically 0.01, 0.05, 0.1  Selected by the researcher or statistician Test statistic – function of the sampled observations that you use for testing a hypothesis Critical/Rejection Region – the set