Technical reserves in non-life insurance

One of the main and crucial activities of an insurance company is to determine amount of technical reserves to be generated. If the insurance company performs in the non-life insurance branch, it focuses first of all on loss reserve which is generated to settle debts coming from insurance claims. To set the proper amount of this reserve, especially of the reserve on incurred but not reported losses (IBNR), mathematical and statistical methods are used. This thesis introduces one of the most used methods which is the chain ladder method. It presents the first chain ladder deterministic model then moves to its stochastic extension in a form of Mack's model and finally gets to the Munich chain ladder model, which takes into calculations not only data on losses paid but also losses incurred. In the theoretical part both these models (standard Mack's chain ladder and Munich chain ladder) are presented both separately and in a common context so that later in the analytical section they could be demonstrated on real data.