Confidence Intervals for Correlation and Proportion

First, this section shows how to compute a confidence interval for Pearson's correlation. The solution uses Fisher's z transformation. Then, it explains the procedure to compute confidence intervals for population proportions where the sampling distribution needs a normal approximation.



  1. We make these corrections because we approximate a discrete distribution with a continuous one.

  2. Because the confidence interval ranges from 51% to 59%, the newspaper must have found that 55% of their sample prefer Candidate A.

  3. Because the confidence interval extends 4% in both directions, the margin of error is 4%. The standard error is sqrt[(.4)(.6)/100] = .0490. The correction = .5/100 = .005. Thus, the upper limit of the 95% confidence interval is: .4 + (1.96)(.049) + .005 = .501. Clearly, there is a large margin of error.