Home | Survey | Topics | Index | References | Dictionary | Contribute | Gallery | Community | Search
| Fitting the power law | Prev topic | Next topic |
Parameters, t (magnitude factor) and s (slope), of the power law y(x) = tx -s are typically estimated by fitting a straight line to log-transformed data [log y, logx]. This yields a biased estimate of the slope, s (for example, Newman 2005).
Goldstein et al (2004) provide a maximum-likelihood-based procedure for evaluating the unbiased value of the slope, s, and hence the constant, t, of the Pareto form of the power law probability distribution. They also tabulate critical values of the goodness-of-fit test based on the Kolmogorov-Smirnow statistics.
| CITATION: Jonasz M. 2006. Fitting the power law (www.tpdsci.com/Tpc/PwLwFit.php). In: Top. Part. Disp. Sci. (www.tpdsci.com). |
HISTORY: Published: 16-Jan-2006 Modified: 29-May-2006 Peer-reviewed: PENDING |
| Journals | Journals search | Contributing | | | Menu |
| Copyright 2005-2012 TPDSci Inc. All rights reserved. | Terms of use | |