***** To join INSNA, visit http://www.sfu.ca/~insna/ *****
Hello SNA folks,
I am trying to find how in-degree centrality relates to resource
exchange and trust.
Here are the steps I took:
1. The in-degree centrality score for each actor was devised from a
communication matrix. This became a vector (attribute data).
2. I correlated in-degree centrality with each matrix for trust and
using Autocorrelation --> Moran statistic (in UCINET).
I received NO SIGNIFICANT findings for any correlation between
in-degree, trust, and resource exchange.
However, I DID received significant results when I ran two other types
1.. I took the matrix data that in-degree centrality was based upon
communication) and used a QAP Correlation.
2. So a QAP Correlation between frequency of communication x trust,
of communication x resource exchange.
I also received significant results when,
1. I converted all the matrices (frequency of communication, trust, and
exchange) into in-degree centrality scores.
2. I then brought these vectors into SPSS and correlated them with one
(I could not do this in UCINET as the program will only run one-way
t-tests on two vectors. As my vectors all pertain to the same sample, I
can not use
UCINET's ANOVA and t-test options).
Can I report on the significant results I received from alternative
2...through using the in-degree scores and correlating them in SPSS? Is
there a problem with mixing applications in this way?
Thanks much in advance to your help, Christina
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.