Q-Q plots with con dence for testing Weibull and exponential distributions

One of the basic graphical methods for assessing the validity of a distributional assumption is the Q-Q plot which compares quantiles of asample against the quantiles of the distribution. In this paper, we focuson how a Q-Q plot can be augmented by intervals for all the points sothat, if the population distribution is Weibull or exponential then allthe points should fall inside the corresponding intervals simultaneouslywith probability 1 - ?. These simultaneous 1 - ? probability intervalsprovide therefore an objective mean to judge whether the plotted pointsfall close to the straight line: the plotted points fall close to the straightline if and only if all the points fall within the corresponding intervals.The powers of ve Q-Q plot based graphical tests and the most popularnon-graphical Anderson-Darling and Cramér-von-Mises tests are compared by simulation. Based on this power study, the tests that havebetter powers are identi ed and recommendations are given on whichgraphical tests should be used in what circumstances. Examples areprovided to illustrate the methods

___

  • Ahsanullah, M. and Hamedani, G.G. Exponential Distribution : Theory and Methods (Nova Science Publishers, Inc. New York, 2010).
  • Blom, G. Statistical Estimates and Transformed Beta Variables (Wiley, New York, 1958).
  • Coles, S.G. On goodness-of- t tests for the 2-parameter Weibull distribution derived from the stabilized probability plot, Biometrika 76(3), 593 598, 1989.
  • Castro-Kuriss, C. On a goodness-of- t test for censored data from a location-scale distri- bution with applications, Chilean Journal of Statistics 2, 115 136, 2011.
  • Chantarangsi, W., Liu, W., Bretz, F., Kiatsupaibul, S., Hayter, A.J. and Fang, W. (2015).
  • Normal probability plots with con dence, Biometrical Journal 57(1), 52 63, 2015.
  • Edwards, D., and Berry, J.J. The E ciency of Simulation-based Multiple Comparisons, Biometrics 43, 913-928, 1987.
  • Filliben, J.J. The probability plot correlation coe cient test for normality, Technometrics , 111-117, 1975.
  • Hazen, A. Storage to be provided in the impounding reservoirs for municipal water supply, Transections of the American Society of Civil Engineers 77, 1547 1550, 1914.
  • Krishnamoorthy, K. Handbook of Statistical distributions with applications {Chapman & Hall/CRC, New York, 2006}.
  • Kimber, A.C. Tests for the exponential, Weibull and Gumbel distributions based on the stabilized probability plot. Biometrika 72(3), 661 663, 1985.
  • Lilliefors, H.W. On the Kolmogorov-Smirnov test for normality with mean and variance unknown. Journal of the American Statistical Association 62(318), 399 402, 1967.
  • Littell, R.C., McClave, J.T. and O en W.W. Goodness-of- t tests for the two parameter Weibull distribution, Communication is Statistics- Simulation and Computation 3, 257 269, Liu, W., Jamshidian, M., Zhang, Y. and J. Donnelly (2005). Simulation-based simultaneous con dence bands in multiple linear regression with predictor variables constrained in intervals, Journal of Computational and Graphical Statistics 14, 459 484, 2005.
  • Lloyd, E.H. Least-squares estimation of location and scale parameters using order statistics, Biometrika 39, 88 95, 1952.
  • Mann, N.R. Optimum estimators for linear functions of location and scale parameters, The Annals of Mathematical Statistics 40, 2149 2155, 1969.
  • Michael, J.R. The stabilized probability plot, Biometrika 70, 11 17, 1983.
  • Pirouzi-Fard, M.N. and Holmquist, B. First moment approximations for order statistics from the extreme value distribution, Statistical Methodology 4, 196 203, 2007.
  • Pirouzi-Fard, M.N. and Holmquist, B. Approximations of variances and covariances for order statistics from the standard extreme value distribution, Communications in Statistics Simulation and Computation 37, 1500 1506, 2008.
  • Pirouzi-Fard, M.N. and Holmquist, B. Powerful goodness-of- t tests for the extreme value distribution, Chilean Journal of Statistics 4(1), 55 67, 2013.
  • Scott, W. F. and Stewart, B. Tables for the Lilliefors and Modi ed Cramer-von Mises tests of normality. Communications in Statistics - Theory and Methods 40(4), 726 730, 2011.
  • Sürücü, B. A power comparison and simulation study of goodness-of- t tests, Computers and Mathematics with Applications 56(6), 1617 1625, 2008
  • Tiku, M.L. and Singh, M. Testing the two parameter Weibull distribution, Communications in Statistics - Theory and Methods 10, 907 918, 1981.
  • Weibull, W. The phenomenon of rupture in solids {Ingeniors Vetenskaps Akademien Handlingar Report, 153, Stockholm, 1939}.