Inferences about the Difference between Two Proportions

This Demonstration explores statistical inferences regarding the difference between two proportions of populations obeying a condition (or trait). It calculates the statistical significance and the confidence intervals for the difference and plots the confidence intervals versus -value. This is done for differing populations obeying a condition or without the condition and for differing -values for the estimation of the confidence intervals.

The statistical significance of the difference between the two proportions is assessed by means of the -score (or critical ratio statistic) [1]. The confidence interval for the difference between the proportions is calculated as in [2].

References

[1] J. L. Fleiss, B. Levin and M. C. Paik, "Methods for Generating a Fourfold Table," Statistical Methods for Rates and Proportions, 3rd ed., Hoboken, NJ: J. Wiley, 2003 pp. 51–52.

[2] J. L. Fleiss, B. Levin and M. C. Paik, "A Simple Confidence Interval for the Difference between Two Independent Proportions," Statistical Methods for Rates and Proportions, 3rd ed., Hoboken, NJ: J. Wiley, 2003 pp. 60–61.