Print

Print


*****  To join INSNA, visit http://www.sfu.ca/~insna/  *****

Use MultiNet. It will take a minute or two at most, depending on your
CPU speed and how much memory your machine has --  not hours. It will
let you decide which three dimensions you want to see, to rotate, zoom,
or pan at will. It will let you use he eigenvector coordinates as a new
variable in any subsequent analysis, and it will let you relate any node
characteristics/variables to the network's structure. It always gives
you a graphic representation of anything it does. Write to Andrew Seary
([log in to unmask]) for more details on how you can use it for two-mode analysis.

cheers,
Bill

Laurence Locklee wrote:

>*****  To join INSNA, visit http://www.sfu.ca/~insna/  *****
>
>I'm trying to analyse a very large 2-mode network with pajek. The data is
>basically about membership of communities of practice, of which I have some
>330 communities and nearly 13,000 unique members. Members typically join
>more than one community (anything from 1 to 30+). What I am hoping to
>identify are how the core communities are related to each other (and
>therefore reflecting the core interests in the company) and also which
>members are closely related to each other based on common interest (and
>perhaps suggesting that these individuals are structurally well placed to
>act as knowledge brokers). I see this as a direct parallel to the davis.net
>example used in the Pajek tutorials. Because of the large size I am
>removing lines and vertices below a theshhold to arrive at the the high
>value relations.
>
>The problem I am having is that in doing the Net/transform/2-mode to
>1-mode/rows and Net/transform/2-mode to 1-mode/Columns, the first one
>working with the 330 communities works well and produces a valued network.
>The second one has to work with the 13,000 members.....it ran for several
>hours and produced a network with no lines! Has anyone had similar
>problems? Are there other ways I could analyse the data say, by using
>Ucinet?
>
>
>Laurence Lock Lee
>
>Principal Knowledge Management Consultant
>Computer Sciences Corporation
>Selwyn St., Port Waratah NSW 2304
>Ph: +61 2 49401777; Fax +61 2 49401865
>Mobile: 0407001628
>E-mail: [log in to unmask]
>
>"Ask, Act, Acknowledge"
>----------------------------------------------------------------------------------------
>
>
>

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