Käärik, Meelis, juhendajaLupul, NicholasTartu Ülikool. Loodus- ja täppisteaduste valdkondTartu Ülikool. Matemaatika ja statistika instituut2023-06-272023-06-272023https://hdl.handle.net/10062/91076The purpose of this master’s thesis is to establish a baseline for what data potential new vehicle insurance providers should collect in order to establish models for claim size. An additional goal was to gather publicly available insurance data sets suitable for modelling claim size and provide an overview of these data sets. The first chapter is used to refresh the reader’s knowledge of generalized linear models. In the second chapter the framework around which the analysis was conducted is introduced and the procedure for the analysis is detailed. The data sets used in the analysis are introduced in chapter three. Chapter four is used to present top models for each data set. The final chapter compares and highlights similarities between top models across the various data sets.engopenAccessAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/generalized additive models for location scale and shapeüldistatud aditiivsed mudelidmootorsõiduki kindlustusmotor vehicle insuranceR (programmeerimiskeel)R (programming language)üldistatud lineaarsed mudelidgeneralized linear modelsinfo:eu-repo/semantics/masterThesis