Document Type

Post-Print

Publication Date

7-11-2014

Subjects

Dynamics -- Mathematical models, Exponential functions, Markov processes, Numerical analysis, Dynamics -- Statistics -- Testing

Abstract

We propose methodology for exact statistical tests of hypotheses for models of network dynamics. The methodology formulates Markovian exponential families, then uses sequential importance sampling to compute expectations within basins of attraction and within level sets of a sufficient statistic for an over-dispersion model. Comparisons of hypotheses can be done conditional on basins of attraction. Examples are presented.

Description

This is the author's accepted manuscript. The final publication, copyright 2014 Institute of Statistical Mathematics, is available at Springer via http://dx.doi.org/10.1007/s10463-014-0472-y.



Persistent Identifier

http://archives.pdx.edu/ds/psu/15321

Download

Share

COinS