Abstract

In the paper we explore an approximate quantiles method to model probability distributions of weather variables such as temperature, radiation, precipitation, wind speed etc. as they vary over time. Our approximate quantile method is based on a new interpretation of M-functionals as quantiles of some probability distribution. A correction factor can be applied and this brings the M-functional very close to the quantiles of the original distribution. In the present research we use a very simple, but non-linear, parametric model to describe the variability of each weather factor over time. By applying our approximate quantiles method for each month, we arrive at five-number summaries of varying-over-time probability distributions. The five numbers show variability over time of approximate quantiles of the considered weather factors.

Full Paper (Size: 542 KB)