HSS 2381 Chapter Notes - Chapter 10: Type I And Type Ii Errors, Frequency Distribution, Analysis Of Variance

• School: University of Ottawa
• Department: Health Sciences
• Course: HSS 2381
• Professor: Eleanor Riesen

Document Summary

Class 10 chi-squared test of goodness of fit, chi-squared test of independence: parametric and nonparametric statistical tests. Parametric statistical tests: tests that rely on population parameters like t-tests & anova; require interval or ratio data. Chi-squared test: ex of non-parametric test; requires only nominal (categorical) data & relies on frequency counts instead of population parameters. Non-parametric tests also known as distribution-free tests. Advantages: numeric scores (ex: interval or ratio data) are classified into several categories, thus, there is no concern about extreme scores, heterogeneous variances are not an issue; It is not necessary for the data to come from a normal distribution: chi-squared test of goodness of fit. The chi-squared goodness-of-fit test uses sample data to test hypotheses about a population distribution. Chi-squared goodness-of-fit test determines how well sample data fit the population characteristics specified by the null hypothesis. Goodness-of-fit test: the observed (sample) frequencies are compared to the expected(population) frequencies.