Sensitivity of normal-based triple sampling sequential point estimation to the normality assumption


Yousef, A.S., Kimber, A.C. and Hamdy, H.I. (2009) Sensitivity of normal-based triple sampling sequential point estimation to the normality assumption Journal of Statistical Planning and Inference, 143, (9), pp. 1606-1618. (doi:10.1016/j.jspi.2013.03.027).

Download

[img] PDF __soton.ac.uk_ude_PersonalFiles_Users_ack1_mydocuments_JSPIpaper_postprint.pdf - Accepted Manuscript
Download (473kB)

Description/Abstract

This article discusses the sensitivity of the sequential normal-based triple sampling procedure for estimating the population mean to departures from normality. We assume only that the underlying population has finite but unknown first four moments and find that asymptotically the behaviour of the estimator and the sample size depend on both the skewness and kurtosis of the underlying distribution, when using a squared error loss function with linear sampling cost. We supplement our findings with a simulation experiment to study the performance of the estimator and the sample size in a range of conditions.

Item Type: Article
Digital Object Identifier (DOI): doi:10.1016/j.jspi.2013.03.027
ISSNs: 0378-3758 (print)
Related URLs:
Keywords: asymptotic relative efficiency, kurtosis, regret, sampling cost, simulation, skewness, squared error loss function, taylor expansion
Subjects:
ePrint ID: 65555
Date :
Date Event
20 February 2009e-pub ahead of print
21 May 2013Published
Date Deposited: 23 Feb 2009
Last Modified: 18 Apr 2017 21:55
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/65555

Actions (login required)

View Item View Item