[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
## Re: [igraph] errors using power.law.fit

**From**: |
Tamas Nepusz |

**Subject**: |
Re: [igraph] errors using power.law.fit |

**Date**: |
Tue, 16 Nov 2010 10:20:20 +0000 |

**User-agent**: |
Mutt/1.5.20 (2009-06-14) |

Hi Martin,
>* thanks for your response. How would one call the C code from R?*
The C code compiles into an executable that you can just call from R
like any other command-line program using system(). So, basically, you
dump the degree distribution to a file, call plfit using system() and
that file as an input, store the output in an R string and then parse
it.
But actually, I was stupid, the authors of that paper have a working
R code here:
http://tuvalu.santafe.edu/~aaronc/powerlaws/
>* Also, the article seems to imply - in the recipe part - that you*
>* estimate the alpha and Xmin parameters, and then test with the*
>* Kolmorgov Smirnov test for goodness of fit. Now, this implies that I*
>* still may run into troubles with the optim() error I got our of R.*
Apparently not, the R code linked above does not use optim(), it uses
some other calculation that seems to give a MLE of alpha given xmin
using an exact formula.
--
Tamas

**[igraph] errors using power.law.fit**, *Martin Tomko*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**, *Tamas Nepusz*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**, *Martin Tomko*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**,
*Tamas Nepusz* **<=**
**Re: [igraph] errors using power.law.fit**, *Gábor Csárdi*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**, *Tamas Nepusz*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**, *Gábor Csárdi*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**, *Martin Tomko*, `2010/11/16`
**Re: [igraph] errors using power.law.fit**, *Gábor Csárdi*, `2010/11/16`

**Re: [igraph] errors using power.law.fit**, *Gábor Csárdi*, `2010/11/16`

**Re: [igraph] errors using power.law.fit**, *Gábor Csárdi*, `2010/11/16`