sim.field.network.stats
Class CentralizationStatistics
java.lang.Object
sim.field.network.stats.CentralizationStatistics
public class CentralizationStatistics
- extends java.lang.Object
Method Summary |
double |
getCentralizationIndexMean(boolean useNormalization)
The average node centrality is Group Centralization for metrics like
Information Centralization (Wasserman and Faust, page 197),
Proximity Prestige (Wasserman and Faust, page 204),
etc.
|
double |
getCentralizationIndexVariance(boolean useNormalization,
boolean unbiased)
|
double |
getGeneralCentralizationIndex()
Computes Freeman's General Centralization Index (Wasserman and Faust, page 177) |
static Bag |
getGraphTheoreticCenter(Network network)
Identifies the points with the smallest maximal distance to all other points. |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
CentralizationStatistics
public CentralizationStatistics(Network network,
NodeIndex metric)
CentralizationStatistics
public CentralizationStatistics(Network network,
FreemanNodeIndex metric)
getCentralizationIndexMean
public double getCentralizationIndexMean(boolean useNormalization)
- The average node centrality is Group Centralization for metrics like
- Information Centralization (Wasserman and Faust, page 197),
- Proximity Prestige (Wasserman and Faust, page 204),
- etc.
getCentralizationIndexVariance
public double getCentralizationIndexVariance(boolean useNormalization,
boolean unbiased)
- Parameters:
unbiased
- according to (Wasserman and Faust, page 180), the sum of (avg - val_i)^2
should be diveded by n. I also offer the unbiased variance (i.e. dividing by n-1).
getGraphTheoreticCenter
public static Bag getGraphTheoreticCenter(Network network)
- Identifies the points with the smallest maximal distance to all other points.
getGeneralCentralizationIndex
public double getGeneralCentralizationIndex()
- Computes Freeman's General Centralization Index (Wasserman and Faust, page 177)