Home > Research > Publications & Outputs > Comparison Between Two Multinomial Overdispersi...

Links

Text available via DOI:

View graph of relations

Comparison Between Two Multinomial Overdispersion Models Through Simulation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Comparison Between Two Multinomial Overdispersion Models Through Simulation. / Afroz, Farzana; Shabuz, Zillur R.
In: Dhaka University Journal of Science, Vol. 68, No. 1, 30.01.2020, p. 45-48.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Afroz F, Shabuz ZR. Comparison Between Two Multinomial Overdispersion Models Through Simulation. Dhaka University Journal of Science. 2020 Jan 30;68(1):45-48. doi: 10.3329/dujs.v68i1.54596

Author

Afroz, Farzana ; Shabuz, Zillur R. / Comparison Between Two Multinomial Overdispersion Models Through Simulation. In: Dhaka University Journal of Science. 2020 ; Vol. 68, No. 1. pp. 45-48.

Bibtex

@article{afee8593a9cf4876969fa003306fc5eb,
title = "Comparison Between Two Multinomial Overdispersion Models Through Simulation",
abstract = "A key assumption when using the multinomial distribution is that the observations are independent. In many practical situations, the observations could be correlated or clustered and the probabilities within each cluster might vary, which may lead to overdispersion. In this paper we discuss two well-known approaches to model overdispersed multinomial data, the Dirichlet-multinomial model and the finite-mixture model. The difference between these two models has been illustrated via simulation study. The forest pollen data is considered as a practical example of overdisperse multinomial data. The overdispersion parameter,φ, has been estimated using two classical estimators.",
author = "Farzana Afroz and Shabuz, {Zillur R.}",
year = "2020",
month = jan,
day = "30",
doi = "10.3329/dujs.v68i1.54596",
language = "English",
volume = "68",
pages = "45--48",
journal = "Dhaka University Journal of Science",
number = "1",

}

RIS

TY - JOUR

T1 - Comparison Between Two Multinomial Overdispersion Models Through Simulation

AU - Afroz, Farzana

AU - Shabuz, Zillur R.

PY - 2020/1/30

Y1 - 2020/1/30

N2 - A key assumption when using the multinomial distribution is that the observations are independent. In many practical situations, the observations could be correlated or clustered and the probabilities within each cluster might vary, which may lead to overdispersion. In this paper we discuss two well-known approaches to model overdispersed multinomial data, the Dirichlet-multinomial model and the finite-mixture model. The difference between these two models has been illustrated via simulation study. The forest pollen data is considered as a practical example of overdisperse multinomial data. The overdispersion parameter,φ, has been estimated using two classical estimators.

AB - A key assumption when using the multinomial distribution is that the observations are independent. In many practical situations, the observations could be correlated or clustered and the probabilities within each cluster might vary, which may lead to overdispersion. In this paper we discuss two well-known approaches to model overdispersed multinomial data, the Dirichlet-multinomial model and the finite-mixture model. The difference between these two models has been illustrated via simulation study. The forest pollen data is considered as a practical example of overdisperse multinomial data. The overdispersion parameter,φ, has been estimated using two classical estimators.

U2 - 10.3329/dujs.v68i1.54596

DO - 10.3329/dujs.v68i1.54596

M3 - Journal article

VL - 68

SP - 45

EP - 48

JO - Dhaka University Journal of Science

JF - Dhaka University Journal of Science

IS - 1

ER -