Test‐Based Exact Confidence Intervals for the Difference of Two Binomial Proportions

Explore this paper's citation graph

Summary

Test-based methods of constructing exact confidence intervals for the difference in two binomial proportions are proposed and it is shown that a large improvement can be achieved by using the standardized Z test with a constrained maximum likelihood estimate of the variance.

Type
article
Published
1999-12-01
Cited by
281
References
17

Keywords

Confidence interval, Statistics, Mathematics, Binomial proportion confidence interval, Robust confidence intervals

References

Cited by

Related papers