Problem
A. Which statistical method should be used to determine if there is a significant relationship between to nominal variables? What are the null and alternative hypotheses for this method and what do they mean?
B. What could happen if a new diagnostic test for diabetes has low sensitivity? What could happen if a new diagnostic test for diabetes has low specificity? What should an analyst do when assessing the usefulness of this test?
C. If two variables are correlated, does that mean one causes the other? Explain
D. If the correlation between the length of stay for a patient and the number of diagnostic tests performed during the stay is positive, then what may be concluded about the slope of the regression line fit between the two variables? What will this regression line look like?