Computes the global envelopes corresponding to the balanced independent two-stage Monte Carlo test of goodness-of-fit.
bits.envelope(X, ...,
nsim = 19, nrank = 1,
alternative=c("two.sided", "less", "greater"),
leaveout=1, interpolate = FALSE,
savefuns=FALSE, savepatterns=FALSE,
verbose = TRUE)An object of class "fv".
Either a point pattern dataset (object of class "ppp",
"lpp" or "pp3") or a fitted point process model
(object of class "ppm", "kppm" or "slrm").
Arguments passed to
mad.test or envelope to
control the conduct of the test.
Useful arguments include fun to determine the summary
function, rinterval to determine the range of
\(r\) values used in the test, and
verbose=FALSE to turn off the messages.
Number of simulated patterns to be generated in each stage.
Number of simulations in each basic test. There will be nsim
repetitions of the basic test, each involving nsim simulated
realisations, together with one independent set of nsim
realisations, so there will be a total
of nsim * (nsim + 1) simulations.
Integer. Rank of the envelope value amongst the nsim simulated
values. A rank of 1 means that the minimum and maximum
simulated values will be used.
Character string determining whether the envelope corresponds
to a two-sided test (alternative="two.sided", the default)
or a one-sided test with a lower critical boundary
(alternative="less") or a one-sided test
with an upper critical boundary (alternative="greater").
Optional integer 0, 1 or 2 indicating how to calculate the deviation between the observed summary function and the nominal reference value, when the reference value must be estimated by simulation. See Details.
Logical value indicating whether to interpolate the distribution of the test statistic by kernel smoothing, as described in Dao and Genton (2014, Section 5).
Logical flag indicating whether to save the simulated function values (from the first stage).
Logical flag indicating whether to save the simulated point patterns (from the first stage).
Logical value determining whether to print progress reports.
Adrian Baddeley, Andrew Hardegen, Tom Lawrence, Robin Milne, Gopalan Nair and Suman Rakshit. Implemented by Adrian Baddeley Adrian.Baddeley@curtin.edu.au.
Computes global simulation envelopes corresponding to the balanced independent two-stage Monte Carlo test of goodness-of-fit described by Baddeley et al (2017). The envelopes are described in Baddeley et al (2019).
If X is a point pattern, the null hypothesis is CSR.
If X is a fitted model, the null hypothesis is that model.
This command is similar to dg.envelope which corresponds
to the Dao-Genton test of goodness-of-fit.
It was shown in Baddeley et al (2017) that
the Dao-Genton test is biased when the significance level is very small
(small \(p\)-values are not reliable) and
we recommend bits.envelope in this case.
Dao, N.A. and Genton, M. (2014) A Monte Carlo adjusted goodness-of-fit test for parametric models describing spatial point patterns. Journal of Graphical and Computational Statistics 23, 497--517.
Baddeley, A., Hardegen, A., Lawrence, T., Milne, R.K., Nair, G. and Rakshit, S. (2017) On two-stage Monte Carlo tests of composite hypotheses. Computational Statistics and Data Analysis 114, 75--87.
Baddeley, A., Hardegen, A., Lawrence, L., Milne, R.K., Nair, G.M. and Rakshit, S. (2019) Pushing the envelope: extensions of graphical Monte Carlo tests. In preparation.
dg.envelope,
bits.test,
mad.test,
envelope
ns <- if(interactive()) 19 else 4
E <- bits.envelope(swedishpines, Lest, nsim=ns)
E
plot(E)
Eo <- bits.envelope(swedishpines, Lest, alternative="less", nsim=ns)
Ei <- bits.envelope(swedishpines, Lest, interpolate=TRUE, nsim=ns)
Run the code above in your browser using DataLab