Rubric

  1. Using a categorical variable with three to five levels (or a categorical variable you can reduce to three to five levels), specify an multinomial goodness-of-fit hypothesis associated with your research questions.
    • (1 p) Specify the goodness-of-fit hypotheses in words and notation,
    • (2 p) plot the data in a way that is consistent with hypothesis test (comparing observed and expected proportions),
    • (1 p) use chisq.test() to calculate the hypothesis test statistic and p-value,
    • (1 p) state the significance level, test statistic, and p-value,
    • (1 p) state the conclusion in the context of the problem, and
    • (1 p) assess the assumptions of the test.
    • (1 p) Plot the contribution to Chi-sq statistic and comment on which groups deviate the most from expected.
    • (2 p) If you rejected the goodness-of-fit null hypothesis, perform follow-up pairwise comparisons using one-sample proportions tests to indicate which groups have statistically different proportions (using Bonferroni to control the Familywise Error Rate) and summarize the results. Otherwise, simply indicate that you did not reject the null hypothesis.

Turn in your master HW file with these sections appended to the bottom.