A study was conducted to determine if a relationship existed between criminal conviction and years of education.17 Sixty people who had taken part in a drug rehabilitation program were classified by years of education. Each person was categorized as having a “short” education (15 years or less) or a “long” education (more than 15 years); also recorded was whether or not they had a post- treatment conviction.
a. Create a logistic regression model using years of education to estimate the probability of conviction. Interpret the model in terms of the odds ratio.
b. Interpret the results of Wald’s test and the LRT.
c. Conduct Fisher’s exact test and a chi-square test of independence (discussed in Chapter 6) using the Convict data. How do these tests compare to the logistic regression model?
d. Report and interpret Somers’ D, Goodman-Kruskal gamma, or Kendall’s tau-a for this logistic regression model.