HOMOGENEITY ASPECTS IN STATISTICAL ANALYSIS OF COASTAL ENGINEERING DATA

P.H.A.J.M. van Gelder, J.K. Vrijling

Abstract


In this paper, the problem of (in)homogeneous data in coastal engineering applications is studied. Statistical analysis of coastal engineering data such as flood data, wind data, wave height data, etc., is essentially a problem of information scarcity. Records are usually too short to ensure reliable estimates of low exceedance probability quantiles in many practical problems. Determination of quantiles is needed for the design, construction and operation of hydraulic structures, insurance studies and protection of populated areas. To perform a frequency analysis of data from coastal engineering practice, the data first has to be tested for homogeneity. Non-homogeneous data may lead to wrong quantiles. A homogeneity test must be able to separate data sets that do not come from the same distribution. In this paper statistical and physical-based homogeneity tests will be presented.

Keywords


homogeneity aspects; statistical analysis

Full Text: PDF

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.