Abstract
Three dispersion measures of a random variable, i.e., the standard deviation, the mean deviation (MD) about the mean and the second L-moment, are analyzed in terms of their properties and mutual relationships. Emphasis is placed on the MD, as it is less recognized than two other dispersion measures. The relationships between the dispersion measures are derived for distributions commonly applied in flood frequency analysis (FFA). For distributions that are unbounded, there is a distribution-dependent constant value of the ratio of dispersion measures, or equivalently of respective coefficients of variation. For two-parameter distributions that are lower-bounded, the relationship between the coefficients of variation is also distribution dependent and is not linear. For lower-bounded three-parameter distributions, the dispersion measure ratios, or equivalently the ratios of coefficients of variation, depend on the coefficient of skewness and show a strong distributional dependence. For selected distributions, the three dispersion measures are compared both in terms of the robustness to the largest samples element and the accuracy of upper quantile estimation. The MD statistics may be highly competitive to the two other dispersion measure statistics if applied in FFA for parameters estimation.
Similar content being viewed by others
References
Barker L (1983) On Gini’s mean difference and the sample standard deviation. Commun Stat Simul Comput 12:503–505
Barker L (1984) On Gini’s mean difference and the sample standard deviation. Commun Stat Simul Comput 13:851–852
Chakrabarti MC (1948) On the ratio of mean deviation to standard deviation. Calcutta Stat Ass Bull 1:187
Cunderlik JM, Burn DH (2003) Non-stationary pooled flood frequency analysis. J Hydrol 276:210–223
Fisher RA (1920) A mathematical examination of the methods of determining the accuracy of an observation by the mean error and by the mean square error. Moth Not R Astr Soc 80:758–769
Gini C (1912) Variabiltà e Mutabilità, contributo allo studio delle distribuzioni e relazioni statistiche. Studi Economico-Giuridici dell’ Univ di Cagliari 3(part 2):1–158
Godwin HJ (1945) On the distribution of the estimate of mean deviation obtained from samples from a normal distribution. Biometrika 33:254
Greenwood JA, Landwehr JM, Matalas NC, Wallis JR (1979) Probability weighted moments: definition and relation to parameters of several distributions expressable in inverse form. Water Resour Res 15:1049–1054
Hosking JRM (1990) L-moments: analysis and estimation of distributions using linear combinations of order statistics. J R Stat Soc B 52:105–124
Hosking JRM, Wallis JR (1987) Parameter and quantile estimation for the generalized Pareto distribution. Technometrics 29:339–349
Hosking JRM, Wallis JR (1997) Regional frequency analysis An approach based on L-moments. Cambridge University Press, Cambridge, p 224
Hosking JRM, Wallis JR, Wood EF (1985) Etimation of the generalized extreme-value distribution by the method of probability-weighted moments. Technometrics 27:251–261
Kamat AR (1965) A property of the mean deviation for a class of continuous distributions. Biometrika 52:288
Kamat AR (1967) Biometrika 54:333
Katsnelson J, Kotz S (1957) On the upper limits of some measures of variability. Archiv F Meteor Geophys U Bioklimat (B) 8:103
Kendall MG, Stuart A (1969) The advanced theory of statistics, vol 1. Distribution theory, Charles Griffin & Comp. Ltd, London
Kendall MG, Stuart A (1973) The advanced theory of statistics, vol 2. Inference and relationship, Charles Griffin & Comp. Ltd, London
Kochanek K, Strupczewski WG, Weglarczyk S, Singh VP (2005) Are the parsimonious FF models more reliable than the true ones? II Comparative assessment of performance of simple models versus the parent distribution. Acta Geophys Pol 53(4):437–457
Kotz S, Johnson NL, Read CB (eds) (1983) Encyclopedia of statistical sciences, vol 6. Wiley, New York, pp 368–369
Kuczera G (1982) Robust flood frequency models. Water Resour Res 18(2):315–324
Landwehr JM, Matalas NC, Wallis JR (1979) Probability-weighted moments compared with some traditional techniques in estimating Gumbel parameters and quantiles. Water Resour Res 15:1055–1064
Landwehr JM, Matalas NC, Wallis JR (1980) Quantile estimation with more or less floodlike distributions. Water Resour Res 16(3):547–555
Patel JK, Read CB (1982) Handbook of the normal distribution. Dekker, New York
Pearson K (1924) Biometrika 16:198–200
Pearson ES, Hartley HO (1966, 1972) Biometrika tables for statisticians, vols 1 and 2. Cambridge University Press, London (see vol 1 Table 21 and vol 2, Table 8)
Plackett RL (1947) Limits of the ratio of mean range to standard deviation. Biometrika 34:120–122
Rao AR, Hamed KH (2000) Flood frequency analysis. CRC, West Palm Beach, p 350
Ryzyk IM, Gradsztejn IS (1971) Tables of integrals, sums and series (in Polish). Nauka, Moscow. Eq (9.14.2) p 1059
Stedinger JR, Vogel MV, Foufoula-Georgiou E (1993) Frequency analysis of extreme events. In: Maidment DR (ed) Handbook of hydrology ch 18. McGraw Hill, New York
Strupczewski WG, Singh VP, Mitosek HT (2001) Non-stationary approach to at- site flood frequency modeling III Flood analysis of Polish rivers. J Hydrol 248:152–167
Strupczewski WG, Singh VP, Weglarczyk S (2002) Asymptotic bias of estimation methods caused by the assumption of false probability distribution. J Hydrol 258:122–148
Wallis JR, Matalas NC, Slack JR (1974) Just a moment! Water Resour Res 10(2):211–19
Wolfram S (1999) The mathematica book, 4th edn. Wolfram Media/ Cambridge University Press, London, p 772
Acknowledgements
This work was supported by the Polish Ministry of Science and Informatics under the Grant 2 P04D 057 29 entitled “Enhancement of statistical methods and techniques of flood events modeling”.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix A
Algebraic bound of variation coefficients
Katsnelson and Kotz (1957) proved that for a set n (≥ 2) non-negative values x i , not all equal, the coefficient of variation (CV=σ/μ) cannot exceed (n − 1)1/2 attaining this value if and only if all but one of the x i values are zero.
For such a set of values one gets the MD
Hence the sampling upper algebraic bound of the coefficient of variation d − CV is
and the asymptotic value δ− CV=2. Proceeding in the same way one finds that for a distribution that takes only positive values, the estimate of the L-coefficient of variation does not have the algebraic bound dependent on the sample size and its value is in the range 0 ⩽ t ⩽ 1.
Appendix B
The δμ/σ ratio for selected distributions.
Taking the uniform distribution \(f{\left(x \right)} = 1/{b;\;x \in {\left[{0,\,b} \right]}}\) one gets \(\sigma = b/{(2{\sqrt 3})}\) and δμ=b / 4. Hence δμ/σ=0.866, which is greater than for the normal distribution (0.798).
For the binomial distribution, i.e., \(P{\left({X = 0} \right)} = p,\quad \;P{\left({X = b} \right)} = q = 1 - p,\) we get \(\sigma = b{\sqrt {q - q^{2}}};\) \(CV = {\sqrt {1/{q - 1}}}\) and δμ=2bq(1 − q) ; δ− CV=2(1 − q). Hence \({\delta _{\mu}}/{\sigma = 2{\sqrt {q - q^{2}}}},\) which gets maximum equal one for q=0.5.
Rights and permissions
About this article
Cite this article
Markiewicz, I., Strupczewski, W.G., Kochanek, K. et al. Relationships between three dispersion measures used in flood frequency analysis. Stoch Environ Res Ris Assess 20, 391–405 (2006). https://doi.org/10.1007/s00477-006-0033-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-006-0033-x