خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Record identifier : 564996
Personal Name - Primary Intelectual Responsibility : Atatalab,Fatemeh
Title and statement of responsibility : A Bayesian Approach to Bonus Malus System An Application in Automobile insurance [Thesis]/عطاطالب، فاطمه;supervisor: Amir Teimour Payandeh;advisor: Ghadir Mahdavi
Publication, Distribution,Etc. : , 2012
Language of the Item : eng
Internal Bibliographies/Indexes Note : Bibliography
Discipline of degree : Actuarial Science
Body granting the degree : , Allameh Tabatabai University, ECO College of Insurance
Summary or Abstract : هدف تحقیق:بررسی و رویکرد بیزی سیستم پاداش - جریمه: کاربرد در بیمه اتومبیل‌می باشد.یافته های تحقیق نشان می دهد که در ارتباط با انتقال دوسیستم که فرمولهای فاصله ای به کار رفته نتایج متفاوتی ایجاد نمی کنند.استفاده از تابع زبان لاینکس موجب می شود که بیمه شده در انتقال بین دو سیستم به سطح پایین تری منقل شود که به سطحش در سیستم قبلی نزدیکتر باشد
: With the deregulation of BMS, it is important to obtain rules in order to transfer policyholders from one BMS to another. This thesis proposes a solution to this problem. It will be shown in this study that an insured who is transferred from a BMS to another one in which level will stay in new system.We contributed to the work of Pitrebois et al. (2006) by applying to Iranian Auto Data. The aim of this thesis is to show how to develop rules allowing to transfer a policyholder from a given BMS to another one. We follow the Norberg method to calculate the relativity premium and use it to obtain measure of discrepancy between two systems. The losses considered in this study are the standard quadratic loss, exponential loss and LINEX loss functions. By a numerical example we show that using exponential loss function and LINEX loss function leads to new levels which are lower than the levels created by using quadratic loss functions. Also this thesis uses credibility factor based on Payandeh (2010) and obtains it for Poisson-Gamma and Zero-inflated Poisson gamma distribution under several loss functions.We observe that the different metrics we have chosen do not provide extremely different results.Using LINEX loss function, the levels in which policyholder is situated are reduced. As much as a is away from zero, the policyholder with LINEX loss function is transferred to lower levels. This means that they will pay lower premiums than when the loss function is exponential or quadratic. When a LINEX loss is used, the size of maluses is reduced..
Uncontrolled Subject Terms : Credibility factor
: LINEX loss function
: Balance-quadratic loss function
: Zero inflated Poisson gamma distribution
: transition rules
: عامل باورمندی
: تابع زیان لاینکس
Information of biblio record : TL
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)