Predictive distribution for polytomous logistic models with nonlinear link functions.
Predictive sample reuse methods usually applied in low structure aparametric paradigms are shown to be useful in certain high structure situations when conjoined with a Bayesian approach. Particular attention is focused on the incomplete data situation for which two alternative sample reuse approaches are devised. The first involves differential weighting and the second a recursive sample reuse algorithm. These are applied to censored exponential survival data. The exponential approach appears to...
Koncept stratifikovaného náhodného výběru představuje užitečnou alternativu prostého náhodného výběru v situaci, kdy je zkoumaná populace složena z několika částí s různými vlastnostmi. Je tak možné například při stejném rozsahu výběru získat odhad průměru s menším rozptylem. V tomto příspěvku si představíme základy teorie stratifikovaných náhodných výběrů a na příkladu druhého kola prezidentských voleb 2023 si ukážeme jejich praktické použití.
For any insurance contract to be mutually advantageous to the insurer and the insured, premium setting is an important task for an actuary. The maximum premium ( that an insured is willing to pay can be determined using utility theory. The main focus of this paper is to determine by considering different forms of the utility function. The loss random variable is assumed to follow different Statistical distributions viz Gamma, Beta, Exponential, Pareto, Weibull, Lognormal and Burr. The theoretical...
Early studies of the novel swine-origin 2009 influenza A (H1N1) epidemic indicate clinical attack rates in children much higher than in adults. Non-medical interventions such as school closings are constrained by their large socio-economic costs. Here we develop a mathematical model to ascertain the roles of pre-symptomatic influenza transmission as well as symptoms surveillance of children to assess the utility of school closures. Our model analysis...
We investigate the properties of a rating migration process assuming that it is given by subordination of a discrete time Markov chain and a Cox process. The problem of pricing of defaultable bonds with fractional recovery of par value with rating migration and credit default swaps is considered. As an example of applications of our results, we give an explicit solution to the pricing problem in a model with short rate and intensity processes given by the solution of a two-dimensional Ornstein-Uhlenbeck...
We apply the results of Baryshnikov, Mayo and Taylor (1998) to calculate non-arbitrage prices of a zero-coupon and coupon CAT bond. First, we derive pricing formulae in the compound doubly stochastic Poisson model framework. Next, we study 10-year catastrophe loss data provided by Property Claim Services and calibrate the pricing model. Finally, we illustrate the values of the CAT bonds tied to the loss data.