Upotreba logističke regresije kod osiguranja vozila

master's thesis

• Author: Marinela Soldo
• Mentor: Anamarija Jazbec (mentor)
• Committee member: Anamarija Jazbec (predsjednik povjerenstva)
• Committee member: Dijana Ilišević (član povjerenstva)
• Committee member: Tina Bosner (član povjerenstva)
• Committee member: Miljenko Marušić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Mathematics); Zagreb
• Defense date and country: 2014-09-23, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

Generalizirani linearni modeli široka su klasa vjerojatnosnih modela koji osiguravaju metode za analizu podataka koji nisu normalno distribuirani. Dopuštaju dva proširenja: distribucija u prvoj komponenti može biti bilo koja distribucija iz eksponencijalne familije, a funkcija veze može biti bilo koja monotona diferencijabilna funkcija [3]. U primjeni je često varijabla od interesa diskretna, odnosno poprima dvije ili više mogućih vrijednosti. Model logističke regresije se najčešće koristi za... More analizu upravo takvih podataka. U prvom poglavlju opisana je teoretska pozadina modela logističke regresije. Definirani su osnovni pojmovi te opisane metode koje koristimo za testiranje značajnosti kovarijata, prilagodbu modela i testiranje adekvatnosti modela. U drugom poglavlju opisana teoretska pozadina modela primijenjena je na aktuarske podatke korištenjem programskog paketa SAS. Less

Abstract (english)

Generalized linear models are a broad class of probabilistic models that provide methods for analyzing data that are not normally distributed. They allow two expansions: distribution in the first component can be any distribution of exponential families, and connection function can be any monotonic differentiable function. In appliance the variable of interest is often a discrete or acquires two or more possible values. The logistic regression is commonly used for the analysis of such data. ... More The first chapter describes the theoretical background of logistic regression. We define the basic concepts and describe the methods for testing the significance of explanatory variables, model fitting and the adequacy of fit. The second chapter is dedicated to the application of the theoretical methods described in chapter 1 to real insurance data using the statistical software package SAS Less

• Keywords: Model logističke regresije; osiguranje vozila
• Keywords (english): logistic regression; car insurance
• Language: croatian
• URN:NBN: urn:nbn:hr:217:669587
• Study programme: Title: Mathematical Statistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Access restricted to students and staff of home institution
• Created on: 2019-02-06 15:42:33