HSS 2381 Chapter Notes - Chapter 17: Test Statistic, Alternative Hypothesis, Heparin

• School: University of Ottawa
• Department: Health Sciences
• Course: HSS 2381
• Professor: Kerry- Ann Hogan

Document Summary

Textbook note chapter 17, note 597-610: outcomes are not measured on an interval or ratio scale and/or, assumptions for parametric test are severely violated. Types of comparison: assumes the sample from known distribution. Tests depends on: -number of groups: being compared -2 vs 3 or more groups from independent groups (btw-subjects design) or from dependent groups (within-subject/repeated measures, correlated groups design) Parametric: strong data-done with higher measurement statistic from a sample & related to reference population eg. z-scores, [t-tests, anova]-looking at assumptions +test hypotheses about parameters. Nonparametric: weak data-done with lower measurement none of the above. No assumptions about population no testing hypotheses about population parameters. Chi-square: distribution that has proven to be particularly useful in statistics commonly used test- statistics are approx. distributed as chi square. Assessing the goodness of fit between observed values and expected tabulated value. Looks at yes/no & nominal measures or ordinal ranking it can not make inferences.