[igraph] Significance level of Kolmogorov-Smirnov test in power_law_fit() output

[Daniele Capocefalo]

Hello everyone,


I was trying to fit a power law on a dataset of ~15K nodes and ~155K edges.

I obtained the following output (from the summary of the PowerLawFit object:

'Fitted power-law distribution on discrete data\n\nExponent (alpha)  = 
3.073111

Cutoff (xmin)     = 141.000000

Log-likelihood    = -1589.823179

H0: data was drawn from the fitted distribution

KS test statistic = 0.024000

p-value           = 0.997102

H0 could not be rejected at significance level 0.05'


so as you can see we are slightly above the critical point for 
scale-freeness assumption.


My question is how to interpret the p-value: H0 in this case means that 
the data are fit to a power law and therefore I can accept  that alpha?


Thanks for your time,


Cheers,


D.


--

———
Daniele Capocefalo
Bioinformatics unit
Casa Sollievo della Sofferenza - Mendel
Viale Regina Margherita 261 - 00198 Roma IT

Tel: +39 06 44160526 - Fax: +39 06 44160548
E-mail: address@hidden
Web page: http://www.css-mendel.it/
Web page: http://bioinformatics.css-mendel.it