In this paper the genetic algorithm is described, applications in the field of statistics are indicated and it is applied to the estimation of the parameters of a Johnson-type distribution. The convergence behaviour is analyzed with respect to the mutation probability, the kind of mutations and...

This article examines the question whether a point and figure (P and F)-based investment strategy yields statistical significant excess returns compared to a buy-and-hold (B and H)-strategy. The simulations show that P and F slightly outperforms B and H with respect to returns as well as with...

This paper considers the problem of parameter estimation when data of a random sample are given in the form of a frequency table. We give special consideration to a method that linearizes the cumulative distribution function. In that case parameters can be derived from the weighted estimation of...

In this paper the efficient market hypothesis in its weak form and the existence of a Monday effect is examined for German stock returns. Using the first order autocorrelation coeffients, a method is developed to test for the existence of finite moments for daily returns. Therefore, simulations...

The Matching Distribution converges to a Poisson Distribution with lambda=1 as the parameter n converges to infinity. A generalization of the Matching Distribution is proposed. The properties of this Generalized Matching Distribution (GMD) turn out to be analogical to the case with lambda=1.

In this paper models for the prediction of matches in the German Soccer Bundesliga are estimated. In a frst step the expected difference of the number of goals is estimated on the basis of estimated abilities of the teams. Here, a focus lies on the necessity of robust parameter estimation. In a...