Confidence Interval for Parameter n in a Binomial Distribution.
Abstract
Consider the binomial distribution b(n,p), where the parameter n represents the number of trials and the parameter p represents the probability of success. When n is fixed in advance after observing k successes, the usual problem is to estimate the probability of success p in the experiment. Situations may also arise when n becomes the unknown parameter of interest. If p is assumed to be known and k successes have been observed, the experimenter would be interested in estimating n instead. Exam search problems. When some threats have been detected in a certain region, the total number of threats in that region becomes a major concern. An estimate of the unknown quantity would be an important consideration in the decision-making process. The next section presents the background and recent development of the problem of estimating n in a binomial distribution. The third section derives the procedure of estimating n in the form of a confidence interval. The last section consists of some concluding remark. A simulation procedure, an interactive computer program, and selected tables are included in the appendixes.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1987
- Accession Number
- ADA178325
Entities
People
- Ronald B. Sindler
- Victor K. Tang
Organizations
- Center for Naval Analyses