P-splines and GAMLSS: a powerful combination, with an application to zero-adjusted distributions

Dimitrios M. Stasinopoulos; Robert A. Rigby; Gillian Z. Heller; Fernanda De Bastiani

doi:10.1177/1471082X231176635

P-splines and GAMLSS: a powerful combination, with an application to zero-adjusted distributions

Dimitrios M. Stasinopoulos^*, Robert A. Rigby, Gillian Z. Heller, Fernanda De Bastiani

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

P-splines are a versatile statistical modelling tool, dealing with nonlinear relationships between the response and explanatory variable(s). GAMLSS is a distributional regression framework which allows modelling of a response variable using any parametric distribution. The combination of the two methodologies provides one of the most powerful tools in modern regression analysis. This article discusses the application of the two techniques when the response variable is zero-adjusted (or semi-continuous), which combines a point probability at zero with a positive continuous distribution.

Original language	English
Pages (from-to)	510-524
Number of pages	15
Journal	Statistical Modelling
Volume	23
Issue number	5-6
DOIs	https://doi.org/10.1177/1471082X231176635
Publication status	Published - Oct 2023
Externally published	Yes

Keywords

Box-Cox t distribution
gamlss
P-splines
semi-continuous distribution
zero-adjusted distribution
zero-heavy distribution

Access to Document

10.1177/1471082X231176635

Cite this

@article{81757615e09d4925a26ec2e4a1959953,

title = "P-splines and GAMLSS: a powerful combination, with an application to zero-adjusted distributions",

abstract = "P-splines are a versatile statistical modelling tool, dealing with nonlinear relationships between the response and explanatory variable(s). GAMLSS is a distributional regression framework which allows modelling of a response variable using any parametric distribution. The combination of the two methodologies provides one of the most powerful tools in modern regression analysis. This article discusses the application of the two techniques when the response variable is zero-adjusted (or semi-continuous), which combines a point probability at zero with a positive continuous distribution.",

keywords = "Box-Cox t distribution, gamlss, P-splines, semi-continuous distribution, zero-adjusted distribution, zero-heavy distribution",

author = "Stasinopoulos, {Dimitrios M.} and Rigby, {Robert A.} and Heller, {Gillian Z.} and {De Bastiani}, Fernanda",

year = "2023",

month = oct,

doi = "10.1177/1471082X231176635",

language = "English",

volume = "23",

pages = "510--524",

journal = "Statistical Modelling",

issn = "1471-082X",

publisher = "SAGE Publications",

number = "5-6",

}

TY - JOUR

T1 - P-splines and GAMLSS

T2 - a powerful combination, with an application to zero-adjusted distributions

AU - Stasinopoulos, Dimitrios M.

AU - Rigby, Robert A.

AU - Heller, Gillian Z.

AU - De Bastiani, Fernanda

PY - 2023/10

Y1 - 2023/10

N2 - P-splines are a versatile statistical modelling tool, dealing with nonlinear relationships between the response and explanatory variable(s). GAMLSS is a distributional regression framework which allows modelling of a response variable using any parametric distribution. The combination of the two methodologies provides one of the most powerful tools in modern regression analysis. This article discusses the application of the two techniques when the response variable is zero-adjusted (or semi-continuous), which combines a point probability at zero with a positive continuous distribution.

AB - P-splines are a versatile statistical modelling tool, dealing with nonlinear relationships between the response and explanatory variable(s). GAMLSS is a distributional regression framework which allows modelling of a response variable using any parametric distribution. The combination of the two methodologies provides one of the most powerful tools in modern regression analysis. This article discusses the application of the two techniques when the response variable is zero-adjusted (or semi-continuous), which combines a point probability at zero with a positive continuous distribution.

KW - Box-Cox t distribution

KW - gamlss

KW - P-splines

KW - semi-continuous distribution

KW - zero-adjusted distribution

KW - zero-heavy distribution

UR - http://www.scopus.com/inward/record.url?scp=85173495519&partnerID=8YFLogxK

U2 - 10.1177/1471082X231176635

DO - 10.1177/1471082X231176635

M3 - Article

AN - SCOPUS:85173495519

SN - 1471-082X

VL - 23

SP - 510

EP - 524

JO - Statistical Modelling

JF - Statistical Modelling

IS - 5-6

ER -

P-splines and GAMLSS: a powerful combination, with an application to zero-adjusted distributions

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this