Discrete Laplace mixture model with applications in forensic genetics

Mikkel Meyer Andersen

doi:10.21105/joss.00748

Abstract

Discrete Laplace mixture model with applications in forensic genetics

Highlights

Estimating haplotype frequencies is important in e.g. forensic genetics, where the frequencies are used to calculate the likelihood ratio for the evidential weight of a DNA profile found at a crime scene (Andersen, Eriksen, and Morling 2013; Steele and Balding 2015)
Estimation is naturally based on a population model, motivating the investigation of the Fisher-Wright model (Fisher 1930; Wright 1931; Ewens 1972; Ohta and Kimura 1973) of evolution for haploid lineage DNA markers
An exponential family called the ‘discrete Laplace distribution’ was described in (Andersen, Eriksen, and Morling 2013) that illustrates how well the discrete Laplace distribution approximates a more complicated distribution that arises by investigating the well-known population genetic Fisher-Wright model of evolution by a single-step mutation process (Caliebe et al 2010)

Summary

Introduction

(and still are) used by multiple groups for e.g. frequency estimation (Andersen, Eriksen, and Morling 2013; S Willuweit and Roewer 2015; S. Willuweit et al 2018; Roewer and Willuweit 2018; Egeland, Kling, and Mostad 2016; Cereda et al 2014; Cereda ative Commons Attribution 4.0 In- 2017), cluster analysis (Andersen, Eriksen, and Morling 2014), and mixture interpretation ternational License (CC-BY). (and still are) used by multiple groups for e.g. frequency estimation Willuweit et al 2018; Roewer and Willuweit 2018; Egeland, Kling, and Mostad 2016; Cereda et al 2014; Cereda ative Commons Attribution 4.0 In- 2017), cluster analysis (Andersen, Eriksen, and Morling 2014), and mixture interpretation ternational License (CC-BY).

Results

Conclusion