Skip to main content

When large n is not enough – Distribution-free interval estimators for ratios of quantiles


Ratios of sample percentiles or of quantiles based on a single sample are often published for skewed income data to illustrate aspects of income inequality, but distribution-free confidence intervals for such ratios are not available in the literature. Here we derive and compare two large-sample methods for obtaining such intervals. They both require good distribution-free estimates of the quantile density at the quantiles of interest, and such estimates have recently become available. Simulation studies for various sample sizes are carried out for Pareto, lognormal and exponential distributions, as well as fitted generalized lambda distributions, to determine the coverage probabilities and widths of the intervals. Robustness of the estimators to contamination or a positive proportion of zero incomes is examined via influence functions and simulations. The motivating example is Australian household income data where ratios of quantiles measure inequality, but of course these results apply equally to data from other countries.

This is a preview of subscription content, access via your institution.


  1. ABS: Household data and income distribution, Austral. Bureau Stat. Report 6523.0. Canberra, ACT. Australia. Available on (2011)

  2. Bonett, D.G., Price, R.M.: Statistical inference for a linear function of medians: Confidence intervals, hypothesis testing, and sample size requirements. Psych. Methods 7, 370–383 (2002)

    Article  Google Scholar 

  3. Cheng, C., Wu, J.: Interval estimation of quantile ratios applied to anti-cancer drug screening by xenograft experiments. Statist. Med. 29, 2669–2678 (2010)

    Article  Google Scholar 

  4. Corlu, C.G., Meterelliyoz, M.: Estimating the parameters of the generalized lambda distribution: which method works best? Commun. Statist. Simulat. (2015)

  5. Cowell, F.A., Victoria-Feser, M.P.: Robustness properties of inequality measures. Econometrica 64(1), 77–101 (1996)

    Article  Google Scholar 

  6. Cowell, F.A., Victoria-Feser, M.P.: Distribution-free inference for welfare indices under complete and incomplete information. J. Econ. Inequal. 1(3), 191–219 (2003)

    Article  Google Scholar 

  7. DasGupta, A.: Asymptotic Theory of Statistics and Probability. Springer New York (2006)

  8. David, H.A.: Order Statistics. Wiley, New York (1981)

  9. De Maio, F.G.: Income inequality measures. J. Epidem. and Comm. Health 61 (10), 849–852 (2007)

    Article  Google Scholar 

  10. Development Core Team, R.: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0 (2008)

  11. Freimer, M., Mudholkar, G.S., Kollia, G., Lin, C.T: A study of the generalized Tukey lambda family. Comm. Statist.- Theory and Methods 17, 3547–3567 (1988)

    Article  Google Scholar 

  12. Genton, M.G.: Comprehensive definitions of breakdown points for independent and dependent observations. J. R. Stat. Soc. Ser. B 65, 81–94 (2003)

    Article  Google Scholar 

  13. Hampel, F.R.: The influence curve and its role in robust estimation. J. Amer. Statist. Assoc. 69, 383–393 (1974)

    Article  Google Scholar 

  14. Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A.: Robust Statistics: The Approach Based on Influence Functions. Wiley, New York (1986)

    Google Scholar 

  15. Hyndman, R.J., Fan, Y.: Sample quantiles in statistical packages. The Amer. Statist. 50, 361–365 (1996)

    Google Scholar 

  16. Johnson, N.L., Kotz, S., Kemp, A.W.: Univariate Discrete Distributions, second edn. Wiley, New York (1993)

    Google Scholar 

  17. King, R., Dean, B., Klinke, S.: gld: Estimation and use of the generalised (Tukey) lambda distribution. R package version 2.2.1 (2014)

  18. Kulinskaya, E., Morgenthaler, S., Staudte, R.G: Variance stabilizing the difference of two binomial proportions. The Amer. Statist. 64, 350–356 (2010)

    Article  Google Scholar 

  19. Morgenthaler, S., Staudte, R.G: Advantages of variance stabilization. Scand. J. Statist. 39, 714–728 (2012)

    Article  Google Scholar 

  20. Parzen, E.: Nonparametric statistical data modeling. J. Amer. Statist. Assoc. 7, 105–131 (1979)

    Article  Google Scholar 

  21. Prendergast, L.A., Staudte, R.G.: Better than you think: interval estimators of the difference of binomial proportions. J. Statist. Plan. Infer. 148, 38–48 (2014)

    Article  Google Scholar 

  22. Prendergast, L.A., Staudte, R.G: Exploiting the quantile optimality ratio to obtain better confidence intervals of quantiles. Stat. 5, 70–81 (2016a)

  23. Prendergast, L.A., Staudte, R.G.: Quantile versions of the Lorenz curve. Electron. J. Statist. 10(2), 1896–1926 (2016b)

  24. Staudte, R.G.: Inference for quantile measures of skewness. TEST 23(4), 751–768 (2014)

    Article  Google Scholar 

  25. Staudte, R.G., Sheather, S.J.: Robust Estimation and Testing. Wiley, New York (1990)

    Book  Google Scholar 

  26. Su, S., et al.: Fitting single and mixture of generalized lambda distributions to data via discretized and maximum likelihood methods: GLDEX in R. J. Statist. Softw. 21(9), 1–17 (2007)

    Article  Google Scholar 

  27. Tukey, J.W.: Which part of the sample contains the information?. Proc. Math. Acad. Sci. USA 53, 127–134 (1965)

    Article  Google Scholar 

  28. Wood, A.: On the bias of order statistics in non-i.i.d. samples. Statist. Prob. Lett. 15, 285–292 (1992)

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Robert G. Staudte.

Electronic supplementary material

Below is the link to the electronic supplementary material.

(PDF 223 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Prendergast, L.A., Staudte, R.G. When large n is not enough – Distribution-free interval estimators for ratios of quantiles. J Econ Inequal 15, 277–293 (2017).

Download citation


  • Generalized lambda distribution
  • Influence function
  • Mixture distribution
  • Quantile density
  • Ratio of percentiles