In risk theory, the total claims of the portfolio during some referenceperiod (e. g. one year)given by S = Xi , where Xi is the claim amountcaused by policy i (i = 1,2,...,n). In the sequel we will always assume that the individual claim amount are nonnegative random variables and that the distribution function Fi of Xi are given.Usually, it is assumed that the risks are mutually independent because models without this restriction turn out to be less manageable.But in real operation, Xi is not always independent. Moreover, theexamples of correlation are very popular. Premium principles are very important to insurance company. When the risks are correlated, the premium of the sum of risks should be newly considered. So, the study in the relation between correlation order and premium principles is very important. Up to now, the study in correlation order and premium principles is limited in the bivariate case and stop-loss premium. this paper studies not only the relation between correlation order and other premium principles, but also the multivariate case. Finally, this paper introduces the two extreme cases of dependence structure and gives some examples in real operation. |