Question: Five hospitals were surveyed regarding a specific surgical procedure designed to improve functioning of certain joints impaired by disease. In this study, "no improvement,” and "improvement" were specifically defined and carefully measured. Interest lay in finding any differences in success between the hospitals.

a. If the five hospitals had the same distribution of successes, compute and display the table of expected counts for hospital C look like (that is to say, under the null hypothesis, what are the expected frequencies for hospital C)?

b. At the .01 level of significance test the null hypothesis that the five hospitals have the same distribution of success in the surgical procedure performed.

c. [No testing here, just data inspection] The researcher suspected that the five hospitals can be combined (some of the hospitals have similar outcomes). Compute the column percentages so that for every hospital, one can see what percentage of patients fall in each of the two success categories. Based on that information ALONE, indicate which hospitals seem to "go together" with which other hospitals.