| quadrat.test.mppm {spatstat.model} | R Documentation |
Chi-Squared Test for Multiple Point Process Model Based on Quadrat Counts
Description
Performs a chi-squared goodness-of-fit test of a Poisson point process model fitted to multiple point patterns.
Usage
## S3 method for class 'mppm'
quadrat.test(X, ...)
Arguments
X |
An object of class |
... |
Arguments passed to |
Details
This function performs a \chi^2 test of goodness-of-fit
for a Poisson point process model, based on quadrat counts.
It can also be used to perform a test of Complete Spatial Randomness
for a list of point patterns.
The function quadrat.test is generic, with methods for
point patterns (class "ppp"), point process models
(class "ppm") and
multiple point process models (class
"mppm").
For this function, the argument X should be a
multiple point process model (object of class "mppm")
obtained by fitting a point process model to a list of
point patterns using the function mppm.
To perform the test, the data point patterns are extracted from X.
For each point pattern
the window of observation is divided into rectangular tiles, and the number of data points in each tile is counted, as described in
quadratcount.-
The expected number of points in each quadrat is calculated, as determined by the fitted model.
Then we perform a single \chi^2 test of goodness-of-fit
based on these observed and expected counts.
Value
An object of class "htest".
Printing the object gives comprehensible output
about the outcome of the test.
The p-value of the test is stored in the
component p.value.
The return value also belongs to
the special class "quadrat.test". Plotting the object
will display, for each window, the position of the quadrats,
annotated by their observed and expected
counts and the Pearson residuals. See the examples.
The return value also has an attribute "components"
which is a list containing the results of
\chi^2 tests of goodness-of-fit
for each individual point pattern.
Testing Complete Spatial Randomness
If the intention is to test Complete Spatial Randomness (CSR) there are two options:
CSR with the same intensity of points in each point pattern;
CSR with a different, unrelated intensity of points in each point pattern.
In the first case,
suppose P is a list of point patterns we want to test.
Then fit the multiple model fit1 <- mppm(P ~1) which signifies a
Poisson point process model with a constant intensity. Then
apply quadrat.test(fit1).
In the second case, fit the model fit2 <- mppm(P ~id)
which signifies a Poisson point process with a different constant
intensity for each point pattern. Then apply quadrat.test(fit2).
Author(s)
Adrian Baddeley Adrian.Baddeley@curtin.edu.au, Ida-Maria Sintorn and Leanne Bischoff. Implemented by Adrian Baddeley Adrian.Baddeley@curtin.edu.au, Rolf Turner rolfturner@posteo.net and Ege Rubak rubak@math.aau.dk.
References
Baddeley, A., Rubak, E. and Turner, R. (2015) Spatial Point Patterns: Methodology and Applications with R. Chapman and Hall/CRC Press.
See Also
Examples
H <- hyperframe(X=waterstriders)
# Poisson with constant intensity for all patterns
fit1 <- mppm(X~1, H)
quadrat.test(fit1, nx=2)
# uniform Poisson with different intensity for each pattern
fit2 <- mppm(X ~ id, H)
quadrat.test(fit2, nx=2)