The behavior of the Wald-z, Wald-c, Quesenberry-Hurst, Wald-m and Agresti-Min methods was investigated for matched proportions confidence intervals. It was concluded that given the widespread use of the repeated-measure design, pretest-posttest design, matched-pairs design, and cross-over design, the textbook Wald-z method should be abandoned in favor of the Agresti-Min alternative.
Reed, James F. III
"Closed Form Confidence Intervals for Small Sample Matched Proportions,"
Journal of Modern Applied Statistical Methods:
2, Article 15.
Available at: http://digitalcommons.wayne.edu/jmasm/vol8/iss2/15