***** To join INSNA, visit http://www.insna.org *****
Katia --
It's not clear from your post how much data is missing. It could be
either a) there were 46 organizations in total and you obtained data
from 27 of them but missed 19; or b) there were 75 organizations in
total and you obtained data from all but 19 of them, a much less serious
problem. Also, you said that the questionnaire was a roster of possible
contacted organizations "even thou it did not include all of them". How
many did it not include? There was a "possibility of adding any
organization with which the interviewed ones had contact with." How
often was this used? Were there many organizations added with this?
It's not possible to say how incomplete your data is without more
information. You might find the 1992 paper Diana Stork and I wrote about
this issue useful . You can see it at:
http://www.insna.org/FAQ/MissingData/S.R.Nonrespondents.pdf
best,
Bill
Tom Valente wrote:
> ***** To join INSNA, visit http://www.insna.org *****
>
> Katia
> With a 41.3% response rate you have some difficulties. Nonetheless,
> it really depends on what you want to do with the data and which
> organizations are missing. One advantage to network data is that you
> still have information on those that are missing. For example, you
> know whether they were nominated often and by whom. I suspect though,
> that your problem will be in missing data on attribute information and
> here is where you will have some difficulty. So I would suggest
> analyzing the network you have and characterize the missing
> organizations. Then specify your research questions and see if the
> missing data affect the research question. - Tom
>
> Katia Pilati wrote:
>
>> ***** To join INSNA, visit http://www.insna.org *****
>>
>> Dear all,
>> I have a doubt concerning the data I have collected on organizations,
>> namely if they can be considered a complete network or a sum of
>> egonetworks. Data represent the entire population of immigrant
>> organizations in a city among which 46 organizations were interviewed
>> and 19 were missing. The questionnaire submitted to the organizations
>> included questions on different kind of relationships that
>> interviewed orgs had with other immigrant orgs. The questionnaire
>> presented a roaster of possible contacted immigrant organizations
>> even thou it did not include all of them and there was a free call
>> possibility of adding any organization with which the interviewed
>> ones had contact with. Due to the missings and the uncomplete list, I
>> wonder if I can consider the interviewed organizations as a complete
>> network or if I should consider them as a sum of egonets.
>> Thank you
>> Katia
>> _____________________________________________________________________
>> 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.
>>
>>
>>
>
_____________________________________________________________________
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.
|