On a flexible construction of a negative binomial model

Fabrizio Leisen, Ramsés H. Mena, Freddy Palma, Luca Rossini

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

This work presents a construction of stationary Markov models with negative-binomial marginal distributions. A simple closed form expression for the corresponding transition probabilities is given, linking the proposal to well-known classes of birth and death processes and thus revealing interesting characterizations. The advantage of having such closed form expressions is tested on simulated and real data.

LanguageEnglish
Pages1-8
Number of pages8
JournalStatistics and Probability Letters
Volume152
DOIs
Publication statusPublished - Sep 2019

Fingerprint

Negative Binomial Model
Closed-form
Birth and Death Process
Negative Binomial
Binomial distribution
Marginal Distribution
Transition Probability
Markov Model
Linking
Negative binomial
Binomial model
Class
Markov model
Transition probability

Keywords

  • Birth and death process
  • Integer-valued time series model
  • Negative-binomial distribution
  • Stationary model

Cite this

Leisen, Fabrizio ; Mena, Ramsés H. ; Palma, Freddy ; Rossini, Luca. / On a flexible construction of a negative binomial model. In: Statistics and Probability Letters. 2019 ; Vol. 152. pp. 1-8.
@article{24e9161b18134c26b27f0a8e516f91d1,
title = "On a flexible construction of a negative binomial model",
abstract = "This work presents a construction of stationary Markov models with negative-binomial marginal distributions. A simple closed form expression for the corresponding transition probabilities is given, linking the proposal to well-known classes of birth and death processes and thus revealing interesting characterizations. The advantage of having such closed form expressions is tested on simulated and real data.",
keywords = "Birth and death process, Integer-valued time series model, Negative-binomial distribution, Stationary model",
author = "Fabrizio Leisen and Mena, {Rams{\'e}s H.} and Freddy Palma and Luca Rossini",
year = "2019",
month = "9",
doi = "10.1016/j.spl.2019.04.004",
language = "English",
volume = "152",
pages = "1--8",
journal = "Statistics and Probability Letters",
issn = "0167-7152",
publisher = "Elsevier",

}

On a flexible construction of a negative binomial model. / Leisen, Fabrizio; Mena, Ramsés H.; Palma, Freddy; Rossini, Luca.

In: Statistics and Probability Letters, Vol. 152, 09.2019, p. 1-8.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - On a flexible construction of a negative binomial model

AU - Leisen, Fabrizio

AU - Mena, Ramsés H.

AU - Palma, Freddy

AU - Rossini, Luca

PY - 2019/9

Y1 - 2019/9

N2 - This work presents a construction of stationary Markov models with negative-binomial marginal distributions. A simple closed form expression for the corresponding transition probabilities is given, linking the proposal to well-known classes of birth and death processes and thus revealing interesting characterizations. The advantage of having such closed form expressions is tested on simulated and real data.

AB - This work presents a construction of stationary Markov models with negative-binomial marginal distributions. A simple closed form expression for the corresponding transition probabilities is given, linking the proposal to well-known classes of birth and death processes and thus revealing interesting characterizations. The advantage of having such closed form expressions is tested on simulated and real data.

KW - Birth and death process

KW - Integer-valued time series model

KW - Negative-binomial distribution

KW - Stationary model

UR - http://www.scopus.com/inward/record.url?scp=85064863579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064863579&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2019.04.004

DO - 10.1016/j.spl.2019.04.004

M3 - Article

VL - 152

SP - 1

EP - 8

JO - Statistics and Probability Letters

T2 - Statistics and Probability Letters

JF - Statistics and Probability Letters

SN - 0167-7152

ER -