On Fixed-Accuracy Confidence Intervals for the Parameters of Lindley Distribution and Its Extensions

Austrian Journal of Statistics

article

Sudeep Bapat¹  Neeraj Joshi²  Ashish Shukla³ 

[1] Indian Institute of Management Indore;University of Delhi;Ramanujan College, University of Delhi

关键词: asymptotic consistency;    asymptotic efficiency;    confidence interval;    fixed - accuracy;    initialmass function;    interval estimation;    Lindley distribution;    sequential estimation;    simulation;   

DOI  :  10.17713/ajs.v52i2.1406

学科分类：医学（综合）

来源: Austrian Statistical Society

【 摘 要 】

The purpose of the present paper is to deal with sequential estimation of the parameter θ in a Lindley distribution. A fixed-accuracy confidence interval for θ with a preassigned confidence coefficient is developed. It is established that, no fixed sample size procedure can solve the estimation problem and hence a purely sequential methodology is proposed to deal with the situation. The first-order asymptotic efficiency and consistency properties associated with our purely sequential strategy are derived. Similar estimation strategies are also outlined for a few other extensions of the Lindley distribution. Extensive simulation analysis is carried out to validate the theoretical findings. We also provide a real data example, where we estimate the parameter related to the “initial mass function" for a particular cluster of stars.

【 授权许可】

CC BY