***** To join INSNA, visit http://www.insna.org *****
I am currently involved in designing a questionnaire to collect some
social network data. In this regard, i had a few queries:
1. How are SN questionnaires typically constructed - all questions asked
personwise or each question asked for all people first before moving to
the next question? Are there any potential concerns in using either of
these methods? Can anyone please point me towards some guidelines of
basic questionnaire construction for SNA?
2. I am interested in collecting data regarding both positive and
negative ties. Since i would like to collect data on other network
variables as well, i have been advised that i can use a common scale
with both positive and negative items (i.e. bipolar scale) in order to
reduce the number of questions that respondents have to answer. Is this
an accepted practice in the Social networks literature? If yes, can i
dichotomize the responses as being positive or negative for my analysis?
Also, if i do use a bipolar scale ranging from say, -3 to +3 , how can i
analyse data regarding the "strength of ties" - positive or negative?
Can i just use part of the scale to do such analyses? How would the
"neutral" part of the scale be treated in that case?
I know ive asked a lot of questions, but i would greatly appreciate any
help / advise from Socnetters .
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.