The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims.

Gillian Heller; Dimitrios Stasinopoulos; Robert Rigby

The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims.

Gillian Heller, Dimitrios Stasinopoulos, Robert Rigby

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

We introduce a method for modelling insurance claim sizes, including zero claims. A mixed discrete-continuous model, with a probability mass at zero and an Inverse Gaussian continuous component, is used. The Inverse Gaussian distribution accommodates the extreme right skewness of the claim distribution. The model explicitly speci¯es a logit-linear model for the occurrence of a claim; and log-linear models for the mean claim size (given a claim has occurred); and the dispersion of claim sizes (given a claim has occurred). The method is illustrated on aa Australian motor vehicle insurance data set.

Original language	English
Title of host publication	Proceedings of the 21st international workshop on statistical modelling
Editors	John Hinde, Jochen Einbeck, John Newell
Place of Publication	Galway, Ireland
Publisher	Statistical Modelling Society
Pages	226-233
Number of pages	8
ISBN (Print)	1862201803
Publication status	Published - 2006
Event	International Workshop on Statistical Modelling (21st : 2006) - Galway, Ireland Duration: 3 Jul 2006 → 7 Jul 2006

Workshop

Workshop	International Workshop on Statistical Modelling (21st : 2006)
City	Galway, Ireland
Period	3/07/06 → 7/07/06

Keywords

Inverse Gaussian model
zero-adjusted
insurance claims
gamlss

Cite this

@inproceedings{b5d72efe3a9e4dd78c74fb55390fae91,

title = "The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims.",

abstract = "We introduce a method for modelling insurance claim sizes, including zero claims. A mixed discrete-continuous model, with a probability mass at zero and an Inverse Gaussian continuous component, is used. The Inverse Gaussian distribution accommodates the extreme right skewness of the claim distribution. The model explicitly speci¯es a logit-linear model for the occurrence of a claim; and log-linear models for the mean claim size (given a claim has occurred); and the dispersion of claim sizes (given a claim has occurred). The method is illustrated on aa Australian motor vehicle insurance data set.",

keywords = "Inverse Gaussian model, zero-adjusted, insurance claims, gamlss",

author = "Gillian Heller and Dimitrios Stasinopoulos and Robert Rigby",

year = "2006",

language = "English",

isbn = "1862201803",

pages = "226--233",

editor = "John Hinde and Jochen Einbeck and John Newell",

booktitle = "Proceedings of the 21st international workshop on statistical modelling",

publisher = "Statistical Modelling Society",

note = "International Workshop on Statistical Modelling (21st : 2006) ; Conference date: 03-07-2006 Through 07-07-2006",

}

Heller, G, Stasinopoulos, D & Rigby, R 2006, The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims. in J Hinde, J Einbeck & J Newell (eds), Proceedings of the 21st international workshop on statistical modelling. Statistical Modelling Society, Galway, Ireland, pp. 226-233, International Workshop on Statistical Modelling (21st : 2006), Galway, Ireland, 3/07/06.

The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims. / Heller, Gillian; Stasinopoulos, Dimitrios; Rigby, Robert.
Proceedings of the 21st international workshop on statistical modelling. ed. / John Hinde; Jochen Einbeck; John Newell. Galway, Ireland: Statistical Modelling Society, 2006. p. 226-233.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims.

AU - Heller, Gillian

AU - Stasinopoulos, Dimitrios

AU - Rigby, Robert

PY - 2006

Y1 - 2006

N2 - We introduce a method for modelling insurance claim sizes, including zero claims. A mixed discrete-continuous model, with a probability mass at zero and an Inverse Gaussian continuous component, is used. The Inverse Gaussian distribution accommodates the extreme right skewness of the claim distribution. The model explicitly speci¯es a logit-linear model for the occurrence of a claim; and log-linear models for the mean claim size (given a claim has occurred); and the dispersion of claim sizes (given a claim has occurred). The method is illustrated on aa Australian motor vehicle insurance data set.

AB - We introduce a method for modelling insurance claim sizes, including zero claims. A mixed discrete-continuous model, with a probability mass at zero and an Inverse Gaussian continuous component, is used. The Inverse Gaussian distribution accommodates the extreme right skewness of the claim distribution. The model explicitly speci¯es a logit-linear model for the occurrence of a claim; and log-linear models for the mean claim size (given a claim has occurred); and the dispersion of claim sizes (given a claim has occurred). The method is illustrated on aa Australian motor vehicle insurance data set.

KW - Inverse Gaussian model

KW - zero-adjusted

KW - insurance claims

KW - gamlss

M3 - Conference proceeding contribution

SN - 1862201803

SP - 226

EP - 233

BT - Proceedings of the 21st international workshop on statistical modelling

A2 - Hinde, John

A2 - Einbeck, Jochen

A2 - Newell, John

PB - Statistical Modelling Society

CY - Galway, Ireland

T2 - International Workshop on Statistical Modelling (21st : 2006)

Y2 - 3 July 2006 through 7 July 2006

ER -

The Zero-adjusted Inverse Gaussian distribution as a model for insurance claims.

Abstract

Workshop

Keywords

Fingerprint

Cite this