Approximate estimations in capture–recapture model with heteroscedastic measurement errors

機構典藏 > College of Sciences > Graduate Institute & Department of Mathematics > Journal Article > Item 987654321/97786

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/97786

Title:	Approximate estimations in capture–recapture model with heteroscedastic measurement errors
Authors:	Hwang, Wen-Han;Huang, Yih-Huei;Chen, Fei-Yin
Contributors:	淡江大學數學學系
Keywords:	differential measurement error;population size;regression calibration;SIMEX;small measurement error
Date:	2013-10
Issue Date:	2014-04-21 15:37:54 (UTC+8)
Publisher:	Abingdon: Taylor & Francis
Abstract:	In a capture–recapture experiment, the number of measurements for individual covariates usually equals the number of captures. This creates a heteroscedastic measurement error problem and the usual surrogate condition does not hold in the context of a measurement error model. This study adopts a small measurement error assumption to approximate the conventional estimating functions and the population size estimator. This study also investigates the biases of the resulting estimators. In addition, modifications for two common approximation methods, regression calibration and simulation extrapolation, to accommodate heteroscedastic measurement error are also discussed. These estimation methods are examined through simulations and illustrated by analysing a capture–recapture data set.
Relation:	Journal of Statistical Computation and Simulation
DOI:	10.1080/00949655.2013.845669
Appears in Collections:	[Graduate Institute & Department of Mathematics] Journal Article

Files in This Item:

File	Description	Size	Format
Approximate estimations in capture–recapture model with heteroscedastic measurement errors.pdf		414Kb	Adobe PDF	0	View/Open
index.html		0Kb	HTML	84	View/Open