Abstract
For a wide range of applications in hydrology and climate studies, the return level is a fundamental quantity to build dykes, propose flood planning policies, and study weather and climate phenomena linked to the behavior of the upper tail of a distribution. More precisely, z t is called the return level associated with a given return period t if the level z t is expected to be exceeded on average once every t years. To estimate this level in the independent and identically distributed setting, Extreme Value Theory (EVT) has been classically used by assuming that exceedances above a high threshold approximately follow a Generalized Pareto distribution (GPD). This approximation is based on an asymptotic argument, but the rate of convergence may be slow in some cases, e.g., Gaussian variables, and the choice of an appropriate threshold difficult. As an alternative, we propose and study simple estimators of lower and upper return level bounds. This approach has several advantages. It works for both small and moderate sample sizes and for discrete and continuous random variables. In addition, no threshold selection procedure is needed. Still, there is a clear link with EVT because our bounds can be viewed as extensions of the concept of the probability weighted moments that has been classically used in hydrology. In particular, some moment conditions have to be satisfied in order to derive the asymptotic properties of our estimators. We apply our methodology to a few simulations and two climate data sets.
Similar content being viewed by others
References
Bonnin G, Todd D, Lin B, Parzybok T, Yekta M, Riley D (2004) NOAA atlas 14, precipitation frequency atlas of the United States, Vol 1 and 2. US Department of Commerce, National Oceanic and Atmospheric Administration, National Weather Service, Silver Spring, Maryland
Coles SG (2001) An introduction to statistical modeling of extreme values. Springer Series in Statistics. Springer, Berlin
Coles S, Dixon M (1999) Likelihood-based inference for extreme value models. Extremes 2:5–23
Cooley D, Nychka DM, Naveau P (2005) Bayesian spatial modeling of extreme precipitation return levels, (In review)
Csörgő M, Csörgő S, Horváth L, Mason DM (1986a) Weighted empirical and quantile process. Ann Probab 14:31–85
Csörgő M, Csörgő S, Horváth L, Mason DM (1986b) Normal and stable convergence of integral functions of the empirical distribution function. Ann Probab 14:86–118
Diebolt J, Guillou A, Rached I (2004) A new look at probability-weighted moments estimators. C R Acad Sci de Paris 7:629–634
Diebolt J, Guillou A, Rached I (2007) Approximation of the distribution of excesses through a generalized probability weighted moment method. J Stat Plan Inference 137:841–857
Einmahl JHJ, Mason DM (1988a) Laws of the iterated logarithm in the tails for weighted uniform empirical processes. Ann Probab 16:126–141
Einmahl JHJ, Mason DM (1988b) Strong limit theorems for weighted quantile processes. Ann Probab 16:1623–1643
Einmahl U, Mason DM (1992) Approximation to permutation and exchangeable processes. J Theor Probab 5:101–126
Embrechts P, Klüppelberg C, Mikosch T (1997) Modelling extremal events for insurance and finance. Springer, Berlin
Helmers R, Janssen P, Serfling R (1990) Berry–Esséen and Bootstrap results for generalized L-statistics. Scand J Statist 17:65–77
Hoskings J, Wallis J (1987) Parameter and quantile estimation for the generalized Pareto distribution. Technometrics 29:339–349
Hoskings J, Wallis J, Wood E (1985) Estimation of the generalized extreme-value distribution by the method of probability-weighted-moments. Technometrics 27:251–261
Katz R, Parlange M, Naveau P (2002) Extremes in hydrology. Adv Water Resour 25:1287–1304
Landwher J, Matalas N, Wallis J (1979) Probability weighted moments compared with some traditional techniques in estimating Gumbel parameters and quantiles. Water Resour Res 15:1055–1064
Leadbetter MR, Lindgren G, Rootzén H (1983) Extremes and related properties of random sequences and processes. Springer, New York
Li D, Rao MB, Tomkins RJ (2001) The law of the iterated logarithm and central limit theorem for L-statistics. J Multivar Anal 78(2):191–217
Philips TK, Nelson R (1995) The moment bound is tighter than Chernoff’s bound for positive tail. Am Stat 49:175–179
Rached I (2004) Moments Pondérés Généralisés. PhD thesis, Université de Marne-la-Vallée, France
Resnick S (1987) Extreme values, regular variation, and point processes. Springer, New York
Shorack GR, Wellner JA (1986) Empirical processes with applications to statistics. Wiley, New York
Wang Q, Jing B-Y, Zhao L (2000) The Berry–Esséen bound for studentized statistics. Ann Probab 28(1):511–535
Wellner JA (1978) Limit theorems for the ratio of the empirical distribution function to the true distribution function. Z Wahrsch Verw Geb 45:73–88
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Guillou, A., Naveau, P., Diebolt, J. et al. Return level bounds for discrete and continuous random variables. TEST 18, 584–604 (2009). https://doi.org/10.1007/s11749-008-0125-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11749-008-0125-7