EC255 Chapter Notes - Chapter 16: Level Of Measurement, Contingency Table, Null Hypothesis
Document Summary
Ec255 chapter 16 textbook: analysis of categorical data. Binomial distribution: only 2 possible outcomes could occur on a single trial in an experiment. Multinomial distribution: more than 2 possible outcomes can occur in a single trial. Chi-square goodness-of-fit test: used to analyze probabilities of multinomial distribution trials along a single dimension. Compares the expected (theoretical) frequencies of categories from a population distribution with the observed (actual) frequencies from a distribution to determine whether there"s a difference between what was expected and what was observed. E. g. can be used to determine whether observed arrivals at teller windows at a bank are. Poisson distributed, or if demand for paper follows a uniform distribution throughout year. Formula compares frequency of observed values with the frequency of the expected values across distribution. Test loses one degree of freedom b/c total number of expected frequencies must = number of observed frequencies. Observed total taken from sample is used as total for expected frequencies.