On the estimation of correlations for irregularly spaced time series

In this paper, the problem of calculating covariances and correlations between time series which are observed irregularly and at different points in time, is treated. The problem of dependence between the time stamp process and the return process is especially highlighted and the solution to this problem for a special case is given. Furthermore, estimators based on different interpolation methods are investigated. The covariances are in turn used to estimate a simple regression on such data. In particular, the difference of first order integrated processes, I(1) processes, are considered. These methods are relevant for stock returns and consequently of importance in e.g. portfolio optimization.