On modeling left-truncated loss data using mixtures of distributions

DOI10.1016/J.INSMATHECO.2018.12.001zbMath1415.62076OpenAlexW2906092815WikidataQ128776091 ScholiaQ128776091MaRDI QIDQ124235

Tatjana Miljkovic, Martin Blostein, Martin Blostein, Tatjana Miljkovic

Publication date: March 2019

Published in: Insurance: Mathematics and Economics, Insurance Mathematics \& Economics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.insmatheco.2018.12.001

zbMATH Keywords

EM algorithmleft-truncationfinite mixture modelsgrid maploss modeling

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to actuarial sciences and financial mathematics (62P05)

Related Items (16)

On automatic bias reduction for extreme expectile estimation ⋮ Gamma mixture density networks and their application to modelling insurance claim amounts ⋮ Mixture Composite Regression Models with Multi-type Feature Selection ⋮ Maximum weighted likelihood estimator for robust heavy-tail modelling of finite mixture models ⋮ Frequency-severity experience rating based on latent Markovian risk profiles ⋮ Soft splicing model: bridging the gap between composite model and finite mixture model ⋮ The Automated Bias-Corrected and Accelerated Bootstrap Confidence Intervals for Risk Measures ⋮ Mixture modeling of data with multiple partial right-censoring levels ⋮ Modeling frequency and severity of claims with the zero-inflated generalized cluster-weighted models ⋮ ROBUST ESTIMATION OF LOSS MODELS FOR LOGNORMAL INSURANCE PAYMENT SEVERITY DATA ⋮ A New Class of Severity Regression Models with an Application to IBNR Prediction ⋮ Extending composite loss models using a general framework of advanced computational tools ⋮ ltmix ⋮ Two-part models for assessing misrepresentation on risk status ⋮ Using Model Averaging to Determine Suitable Risk Measure Estimates ⋮ Fitting Censored and Truncated Regression Data Using the Mixture of Experts Models

Uses Software

• R
• DEoptim

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models
• Choosing initial values for the EM algorithm for finite mixtures
• Estimating the dimension of a model
• Bayesian model averaging: A tutorial. (with comments and a rejoinder).
• Modelling censored losses using splicing: a global fit strategy with mixed Erlang and extreme value distributions
• Modeling loss data using composite models
• Modeling loss data using mixtures of distributions
• Composite Lognormal–Pareto model with random threshold
• Science and Statistics
• Model-Based Clustering, Discriminant Analysis, and Density Estimation
• Finite mixture models
• Model Selection and Multimodel Inference
• FITTING MIXTURES OF ERLANGS TO CENSORED AND TRUNCATED DATA USING THE EM ALGORITHM
• Modeling claims data with composite Stoppa models
• Toward a Unified Approach to Fitting Loss Models
• Modeling with Weibull-Pareto Models
• On composite lognormal-Pareto models
• A new look at the statistical model identification

This page was built for publication: On modeling left-truncated loss data using mixtures of distributions