Premium
Interval estimation of population parameters based on environmental data with detection limits
Author(s) -
Peng Cheng
Publication year - 2010
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.1024
Subject(s) - confidence interval , censoring (clinical trials) , statistics , confidence distribution , cdf based nonparametric confidence interval , robust confidence intervals , population , mathematics , econometrics , estimation , demography , engineering , systems engineering , sociology
In this paper, we focus on constructing confidence intervals of normal population parameters based on multiple left‐censored samples (singly and doubly censored samples are special cases). In addition to the asymptotic confidence interval, we propose a bootstrap procedure based on type I left censored samples with multiple censoring limits and use it to construct bootstrap confidence intervals for the population parameters of interest. Guidelines of selecting either asymptotic or bootstrap confidence intervals for practitioners are provided. We also provide some illustrative examples using real‐life data. Copyright © 2009 John Wiley & Sons, Ltd.