Parametric and nonparametric estimators of ED100α

Dongryeon Park, Sangun Park

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In bioassay, the logit model is the most widely used parametric model. However, the exact form of the response curve is usually unknown and even very complicated, so it is likely that the true model does not follow the logit model. Therefore, according to well-known asymptotic results, when the sample size is very large, we should probably use the non-parametric regression rather than the logit model unless the exact form of the true response curve is known. In practice, however, we can not increase the sample size infinitely, so the asymptotic result would not be so useful. In this article, we would like to compare the small sample properties of the logit model and the non-parametric estimator. As the non-parametric method, we choose the locally weighted quasi-likelihood estimator. A Monte Carlo study was done under various circumstances, and it turned out that the locally weighted quasi-likelihood estimator is very competitive in the small sample situation.

Original languageEnglish
Pages (from-to)661-672
Number of pages12
JournalJournal of Statistical Computation and Simulation
Volume76
Issue number8
DOIs
Publication statusPublished - 2006 Aug 1

Fingerprint

Logit Model
Nonparametric Estimator
Quasi-likelihood
Small Sample
Sample Size
Estimator
Bioassay
Curve
Nonparametric Methods
Nonparametric Regression
Monte Carlo Study
Parametric Model
Choose
Likely
Unknown
Logit model
Form
Sample size

All Science Journal Classification (ASJC) codes

  • Applied Mathematics
  • Statistics and Probability
  • Modelling and Simulation

Cite this

@article{8b38443802b44def9575e6407377c378,
title = "Parametric and nonparametric estimators of ED100α",
abstract = "In bioassay, the logit model is the most widely used parametric model. However, the exact form of the response curve is usually unknown and even very complicated, so it is likely that the true model does not follow the logit model. Therefore, according to well-known asymptotic results, when the sample size is very large, we should probably use the non-parametric regression rather than the logit model unless the exact form of the true response curve is known. In practice, however, we can not increase the sample size infinitely, so the asymptotic result would not be so useful. In this article, we would like to compare the small sample properties of the logit model and the non-parametric estimator. As the non-parametric method, we choose the locally weighted quasi-likelihood estimator. A Monte Carlo study was done under various circumstances, and it turned out that the locally weighted quasi-likelihood estimator is very competitive in the small sample situation.",
author = "Dongryeon Park and Sangun Park",
year = "2006",
month = "8",
day = "1",
doi = "10.1080/10629360500279706",
language = "English",
volume = "76",
pages = "661--672",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "8",

}

Parametric and nonparametric estimators of ED100α. / Park, Dongryeon; Park, Sangun.

In: Journal of Statistical Computation and Simulation, Vol. 76, No. 8, 01.08.2006, p. 661-672.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Parametric and nonparametric estimators of ED100α

AU - Park, Dongryeon

AU - Park, Sangun

PY - 2006/8/1

Y1 - 2006/8/1

N2 - In bioassay, the logit model is the most widely used parametric model. However, the exact form of the response curve is usually unknown and even very complicated, so it is likely that the true model does not follow the logit model. Therefore, according to well-known asymptotic results, when the sample size is very large, we should probably use the non-parametric regression rather than the logit model unless the exact form of the true response curve is known. In practice, however, we can not increase the sample size infinitely, so the asymptotic result would not be so useful. In this article, we would like to compare the small sample properties of the logit model and the non-parametric estimator. As the non-parametric method, we choose the locally weighted quasi-likelihood estimator. A Monte Carlo study was done under various circumstances, and it turned out that the locally weighted quasi-likelihood estimator is very competitive in the small sample situation.

AB - In bioassay, the logit model is the most widely used parametric model. However, the exact form of the response curve is usually unknown and even very complicated, so it is likely that the true model does not follow the logit model. Therefore, according to well-known asymptotic results, when the sample size is very large, we should probably use the non-parametric regression rather than the logit model unless the exact form of the true response curve is known. In practice, however, we can not increase the sample size infinitely, so the asymptotic result would not be so useful. In this article, we would like to compare the small sample properties of the logit model and the non-parametric estimator. As the non-parametric method, we choose the locally weighted quasi-likelihood estimator. A Monte Carlo study was done under various circumstances, and it turned out that the locally weighted quasi-likelihood estimator is very competitive in the small sample situation.

UR - http://www.scopus.com/inward/record.url?scp=33745120164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745120164&partnerID=8YFLogxK

U2 - 10.1080/10629360500279706

DO - 10.1080/10629360500279706

M3 - Article

AN - SCOPUS:33745120164

VL - 76

SP - 661

EP - 672

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 8

ER -