Date Thesis Awarded

4-2020

Document Type

Honors Thesis

Degree Name

Bachelors of Science (BS)

Department

Mathematics

Advisor

Lawrence Leemis

Committee Members

Heather Sasinowska

Carl Moody

Abstract

Let X1, X2, . . . , Xn be independent and identically distributed Bernoulli(p) random variables with unknown parameter p satisfying 0 < p < 1. Let X = Pn i=1 Xi be the number of successes in the n mutually independent Bernoulli trials. The maximum likelihood estimator of p is ˆp = X/n. For fixed n and α, there are n + 1 distinct 100(1 − α)% confidence intervals associated with X = 0, 1, 2, . . . , n. Currently there is no known exact confidence interval for p. Our goal is to construct the confidence interval for p whose actual coverage is closest to the stated coverage, using the root mean squared error, RMSE, to measure the difference between the actual coverage and the stated coverage. The approximate confidence interval for p developed here minimizes the RMSE for a sample size n and a significance level α.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS