Geography Reference
In-Depth Information
Table 14
.
2
Bivariate QAP regression analysis: all sales alliances in 2005
Independent variables
Regression coei cient
R
2 (adjusted)
Observations
A
.
Homophily
Firm age
0.000
0.000
2070
Digital entry
0.002*
0.003
1560
Size employment
0.001*
0.009*
1332
Size images
0.000
0.000
2450
Size photographers
0.001
0.000
1806
Universality
0.002
0.000
2756
Specialization
0.016*
0.002*
2756
International sales
0.000
0.000
1190
Lobby association
0.012**
0.002**
4830
B
.
Geography
Colocation
0.023**
0.004**
2652
C
.
Popularity bias
Indegree centrality
0.002**
0.006**
4830
Outdegree centrality
0.001*
0.004*
4830
D
.
Multiconnectivity
Point connectivity
0.229**
0.220**
4830
Geodesic count
0.207**
0.195**
4830
*
p
< 0.05; **
p
< 0.01; 2000 random permutations.
One third of alliances however forms a rather peripheral landscape of various uncon-
nected and isolated alliances. In the next analytic section, social network analysis is used
to search for an explanation of this emerging network structure.
Explaining tie formation in the rights-managed sales alliance network
This section applies the hypotheses on network growth to the domestic RM alliance
network in Germany. Two sets of analyses are carried out. First, in a static perspective
the independent variables are tested against the network of sales alliances all in the same
year 2005. The results for bivariate QAP regressions are summarized in Table 14.2. This
produces a number of signii cant explanatory variables for further analysis. Second, and
in a dynamic perspective, signii cant variables from the i rst set of regressions in the year
2005 are used for a year-to-year longitudinal analysis between 1995 and 2005. Each inde-
pendent variable from one year
t
n
is compared to the alliance network structure of the
subsequent year
t
n+
1
thus providing a year-to-year estimation of the hypothesized ef ect
on the new network structure in the subsequent year. The regression ef ects for the four
hypotheses are found to be quite dif erent.
Homophily
Arguments about preferential partner selection based on homophily suggest
that the more similar two partners are to each other, the more likely will they engage in
a relationship. However, this proposition receives hardly any support in the context
of the alliance network between picture agencies. Most of the similarity variables are
