Mixture Representations and Inference for the Voigt Profile

ABSTRACT The Voigt profile is the density resulting from the convolution of a Gaussian and a Cauchy density. A representation of the Voigt profile in terms of elementary functions does not exist and the usual estimation approach is based on approximating the complex error function (Faddeeva) in the density before fitting the empirical profile. In this paper we discuss mixture characterizations of the Voigt profile which allow parameter estimation in a Bayesian framework without the need to approximate the Faddeeva function. Monte Carlo simulations show that the proposed approach outperforms traditional numerical fitting methods, achieving better Bayesian coverage, lower mean square error across all parameter combinations, and generally faster computation. The approach can be applied to empirical Voigt profile data and it is illustrated through a case study involving the dating of ancient artifacts based on Voigt spectral line‐shapes, which capture the chemical signatures of dyes present on their surfaces.

Authors

Institutions

Publication Details

Journal
Statistical Analysis and Data Mining The ASA Data Science Journal
Published
2026-11-17
DOI
https://doi.org/10.1002/sam.70127
Primary Topic
Bayesian Methods and Mixture Models
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Mixture Representations and Inference for the Voigt Profile

Massimo Cannas, Nicola Piras
Statistical Analysis and Data Mining The ASA Data Science Journal
Bayesian Methods and Mixture Models
article

Mixture Representations and Inference for the Voigt Profile

Massimo Cannas, Nicola Piras
article en

Abstract

ABSTRACT The Voigt profile is the density resulting from the convolution of a Gaussian and a Cauchy density. A representation of the Voigt profile in terms of elementary functions does not exist and the usual estimation approach is based on approximating the complex error function (Faddeeva) in the density before fitting the empirical profile. In this paper we discuss mixture characterizations of the Voigt profile which allow parameter estimation in a Bayesian framework without the need to approximate the Faddeeva function. Monte Carlo simulations show that the proposed approach outperforms traditional numerical fitting methods, achieving better Bayesian coverage, lower mean square error across all parameter combinations, and generally faster computation. The approach can be applied to empirical Voigt profile data and it is illustrated through a case study involving the dating of ancient artifacts based on Voigt spectral line‐shapes, which capture the chemical signatures of dyes present on their surfaces.

Statistical Analysis and Data Mining The ASA Data Science JournalVol. 19(6)
University of Cagliari (IT)
Bayesian Methods and Mixture Models
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon