Problems with fitting to the power-law distribution
- 2.5k Downloads
This short communication uses a simple experiment to show that fitting to a power law distribution by using graphical methods based on linear fit on the log-log scale is biased and inaccurate. It shows that using maximum likelihood estimation (MLE) is far more robust. Finally, it presents a new table for performing the Kolmogorov-Smirnov test for goodness-of-fit tailored to power-law distributions in which the power-law exponent is estimated using MLE. The techniques presented here will advance the application of complex network theory by allowing reliable estimation of power-law models from data and further allowing quantitative assessment of goodness-of-fit of proposed power-law models to empirical data.
KeywordsEmpirical Data Maximum Likelihood Estimation Likelihood Estimation Complex Network Reliable Estimation
Unable to display preview. Download preview PDF.
- 3.M. Faloutsos, P. Faloutsos, C. Faloutsos, Computer Commun. Rev. 29, 251 (1999)Google Scholar
- 6.N.L. Johnson, S. Kotz, A.W. Kemp, Univariate discrete distributions (John Wiley & Sons, New York, 1992)Google Scholar
- 9.M.E.J. Newman, SIAM Rev. 45, 157 (2003)Google Scholar
- 13.P.T. Nicholls, J. Am. Soc. Information Sci. 40, 379 (1989)Google Scholar
- 14.A.N. Kolmogorov, Giornale dell’ Instituto Italiano degli Attuari 4, 77 (1933)Google Scholar
- 16.W.J. Conover, Practical nonparametric statistics (Wiley, New York, 1999)Google Scholar
- 17.H.W. Lilifoers, J. Am. Stat. Asso. 62, 399 (1967)Google Scholar
- 18.H.W. Lilifoers, J. Am. Stat. Asso. 64, 387 (1969)Google Scholar
- 19.A.J. Lotka, J. Washington Academy of Sciences 16, 317 (1926)Google Scholar