Modeling and inference of forest coverage ratio using zero-one inflated distributions with spatial dependence

Ryuei Nishii, Shojiro Tanaka

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper explores statistical modeling of forest area with two covariates. The forest coverage ratio of grid-cell data was modeled by taking human population density and relief energy into account. The likelihood of the forest ratios was decomposed into the product of two likelihoods. The first likelihood was due to trinomial logistic distributions on three categories: the forest ratios take zero, or one, or values between zero and one. The second one was due to a logistic-normal regression model for the ratios between zero and one. This model was applied to real grid-cell data and it fit better than zero-inflated beta regression models.

Original languageEnglish
Pages (from-to)315-336
Number of pages22
JournalEnvironmental and Ecological Statistics
Volume20
Issue number2
DOIs
Publication statusPublished - Jun 1 2013

Fingerprint

Spatial Dependence
Coverage
Likelihood
Zero
Modeling
modeling
logistics
Regression Model
Grid
Logistics/distribution
Statistical Modeling
Cell
Logistics
Covariates
population density
relief
distribution
Spatial dependence
Inference
Energy

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Environmental Science(all)
  • Statistics, Probability and Uncertainty

Cite this

Modeling and inference of forest coverage ratio using zero-one inflated distributions with spatial dependence. / Nishii, Ryuei; Tanaka, Shojiro.

In: Environmental and Ecological Statistics, Vol. 20, No. 2, 01.06.2013, p. 315-336.

Research output: Contribution to journalArticle

@article{c1e0c4e5a9ec40d0a6f514a8b2cbe592,
title = "Modeling and inference of forest coverage ratio using zero-one inflated distributions with spatial dependence",
abstract = "This paper explores statistical modeling of forest area with two covariates. The forest coverage ratio of grid-cell data was modeled by taking human population density and relief energy into account. The likelihood of the forest ratios was decomposed into the product of two likelihoods. The first likelihood was due to trinomial logistic distributions on three categories: the forest ratios take zero, or one, or values between zero and one. The second one was due to a logistic-normal regression model for the ratios between zero and one. This model was applied to real grid-cell data and it fit better than zero-inflated beta regression models.",
author = "Ryuei Nishii and Shojiro Tanaka",
year = "2013",
month = "6",
day = "1",
doi = "10.1007/s10651-012-0227-y",
language = "English",
volume = "20",
pages = "315--336",
journal = "Environmental and Ecological Statistics",
issn = "1352-8505",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Modeling and inference of forest coverage ratio using zero-one inflated distributions with spatial dependence

AU - Nishii, Ryuei

AU - Tanaka, Shojiro

PY - 2013/6/1

Y1 - 2013/6/1

N2 - This paper explores statistical modeling of forest area with two covariates. The forest coverage ratio of grid-cell data was modeled by taking human population density and relief energy into account. The likelihood of the forest ratios was decomposed into the product of two likelihoods. The first likelihood was due to trinomial logistic distributions on three categories: the forest ratios take zero, or one, or values between zero and one. The second one was due to a logistic-normal regression model for the ratios between zero and one. This model was applied to real grid-cell data and it fit better than zero-inflated beta regression models.

AB - This paper explores statistical modeling of forest area with two covariates. The forest coverage ratio of grid-cell data was modeled by taking human population density and relief energy into account. The likelihood of the forest ratios was decomposed into the product of two likelihoods. The first likelihood was due to trinomial logistic distributions on three categories: the forest ratios take zero, or one, or values between zero and one. The second one was due to a logistic-normal regression model for the ratios between zero and one. This model was applied to real grid-cell data and it fit better than zero-inflated beta regression models.

UR - http://www.scopus.com/inward/record.url?scp=84878414730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878414730&partnerID=8YFLogxK

U2 - 10.1007/s10651-012-0227-y

DO - 10.1007/s10651-012-0227-y

M3 - Article

AN - SCOPUS:84878414730

VL - 20

SP - 315

EP - 336

JO - Environmental and Ecological Statistics

JF - Environmental and Ecological Statistics

SN - 1352-8505

IS - 2

ER -