Print

Print


*****  To join INSNA, visit http://www.insna.org  *****

you might be able (should be?) to find a mapping (new coordinate
system) such that the two distributions are topologically equivalent,
and then use that to "normalize" across the two distributions.

talk to a math guru :-)

-p

On Dec 5, 2007 3:49 AM, Eelke Heemskerk <[log in to unmask]> wrote:
> *****  To join INSNA, visit http://www.insna.org  *****
>
> Dear Socnetters,
>
>
>
> In a network of interlocking directorates, I have the (edge)degree
> distributions at two time periods. Now I would like to say something about
> the significance of the differences between the mean degrees (it drops).
>
>
>
> However, it seems that simple mean comparisons won't do the job since these
> assume a normal distribution, which is not the case with edge degree in
> these networks. I came across Mann-Whitney, which seems to be better suited.
> However, I am not familiar with it and might overlook important assumptions.
>
>
>
> Any suggestions on the best way to say something about significance of
> difference in means of degree distributions?
>
>
>
> Thanks,
>
>
>
> Eelke
>
>
>
>
>
> de Galan Groep
> Rutgers van Rozenburglaan 2
> 3744 MC Baarn
> Tel.: 035 - 69 48 000
> Fax.: 035 - 69 48 200
> www.galangroep.nl
> KvK Gooi-en Eemland nr. 32059625
>
>
>
>
>
>
> _____________________________________________________________________
> SOCNET is a service of INSNA, the professional association for social
> network researchers (http://www.insna.org). To unsubscribe, send
> an email message to [log in to unmask] containing the line
> UNSUBSCRIBE SOCNET in the body of the message.
>



-- 
--------------------------------------------------------
http://www.PaulBHartzog.org
http://www.panarchy.com
[log in to unmask]
[log in to unmask]
[log in to unmask]
--------------------------------------------------------
The Universe is made up of stories, not atoms.
                 --Muriel Rukeyser

See differently, then you will act differently.
                 --Paul B. Hartzog
--------------------------------------------------------

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.