CRIM 320 Lecture Notes - Lecture 4: Null Hypothesis
6 Oct 2016
School
Department
Course
Professor
Document Summary
Normal distribution (known areas in curve) when we do not have normal distribution. Chi-square test of independence the basic idea of chi-square. One-way chi-square is similar to one sample t test. If we reject the null, we are stating that the two variables are dependent. Chi-square independence vs dependence the logic of chi-square. Observed: actual data collected from your sample (actual numbers in each category of variables in dataset) Expected counts: info we expect to have on variables if the data was independence. Reject the null if the observed counts are sufficiently different from the expected counts. Compare observed with expected, to determine if we can reject the null hypothesis example: prison misconducts. Data taken from table 1 in camp and gaes article. Whether or not intensities of incarceration would make inmates engage in more misconduct. Column and row marginal are same as totals represent each category variable. Row total x column total / grand total.
