In environmental risk analysis, it is common to assume the stochastic independence (or separability) between the marks associated with the random events of a spatial-temporal point process. Schoenberg (2004, Biometrics 60, 471-481) proposed several test statistics for this hypothesis and used simulated data to evaluate their performance. He found that a Cramér-von Mises-type test is powerful to detect gradual departures from separability although it is not uniformly powerful over a large class of alternative models. We present a semiparametric approach to model alternative hypotheses to separability and derive a score test statistic. We show that there is a relationship between this score test and some of the test statistics proposed by Schoenberg. Specifically, all are different versions of weighted Cramér-von Mises-type statistics. This gives some insight into the reasons for the similarities and differences between the test statistics' performance. We also point out some difficulties in controlling the type I error probability in Schoenberg's residual test.
[1]
Frederic Paik Schoenberg,et al.
Transforming Spatial Point Processes into Poisson Processes
,
1999
.
[2]
F. Schoenberg.
Testing Separability in Multi-dimensional Point Processes
,
2003
.
[3]
A. Pallini.
Simultaneous confidence bands for pair correlation functions in Markov point processes
,
2002
.
[4]
Peter J. Diggle,et al.
Detecting dependence between marks and locations of marked point processes
,
2004
.
[5]
Frederic Paik Schoenberg,et al.
Testing separability in spatial-temporal marked point processes.
,
2004,
Biometrics.
[6]
Donald L. Snyder,et al.
The statistical analysis of space-time point processes
,
1976,
IEEE Trans. Inf. Theory.
[7]
Patricia L. Andrews,et al.
Introduction To Wildland Fire
,
1984
.