CHANGES IN spatstat.core VERSION 2.3-2
OVERVIEW
o More diagnostics for spatial logistic regression models.
o Important bug fix in kppm.
o Increased numerical stability in kppm.
o Minor improvements and bug fixes.
o We thank Jonas Brehmer for contributions.
NEW FUNCTIONS
o lurking.slrm
Lurking variable plot for spatial logistic regression models.
o eem.slrm
Exponential energy marks for spatial logistic regression models.
o eem.ppm
Exponential energy marks for Gibbs and Poisson point process models
(this function was previously called 'eem').
SIGNIFICANT USER-VISIBLE CHANGES
o eem
The function 'eem' is now generic, with methods for 'ppm' and 'slrm'.
The function previously named 'eem' is now called 'eem.ppm'.
o objsurf.dppm, objsurf.kppm, objsurf.mincontrast
New arguments 'xlim', 'ylim' determine the range of parameter values
to be considered.
o Hybrid
Printed output from hybrid models has been improved slightly.
o kppm
New default settings ensure greater numerical stability of the
optimization algorithm against the effects of the scale of the
spatial coordinates. New argument 'stabilize' specifies whether
the optimization algorithm should be numerically stabilized.
o pcf
Improved error message
BUG FIXES
o kppm
Results were sometimes incorrect for method='clik2' and method='palm'
because the log composite likelihood was erroneously truncated to
positive values. Any fitted model for which logLik(model) = 2.2e-16
should be suspected of being incorrect.
Fixed.
o edge.Ripley
Results were incorrect for data points lying exactly at the corners
of a rectangle.
Fixed.
o MultiHard
A hybrid of 'MultiHard' with another multitype interaction caused an error.
Fixed.
o simulate.dppm, simulate.detpointprocfamily
Crashed, rarely, with error message 'The dimension differs from the number of columns in index'.
Fixed.
o as.fv.kppm, as.fv.dppm
The default plot labels in 'as.fv(x)' implied that the model 'x' was inhomogeneous.
Fixed.
CHANGES IN spatstat.core VERSION 2.3-1
OVERVIEW
o Covariates in ppm and mppm may be functions that depend on the marks
as well as the spatial coordinates.
o Automatic selection of threshold for defining a binary predictor.
o Random perturbation of line segments.
o Minor extensions, performance improvements, and bug fixes.
NEW FUNCTIONS
o thresholdSelect, thresholdCI
Select the optimal threshold for converting a numerical predictor
to a binary predictor.
o coef<-.fii
Changes the coefficients of a fitted interaction object
(a method for the generic "coef<-")
o rjitter.psp
Random perturbation of a spatial pattern of line segments.
A method for 'rjitter' for class 'psp'.
SIGNIFICANT USER-VISIBLE CHANGES
o ppm
Covariates which are functions may now depend on the marks
as well as the spatial coordinates: function(x,y,marks).
o mppm
Covariates which are functions may now depend on the marks
as well as the spatial coordinates: function(x,y,marks).
o reach.kppm
Now returns a result for LGCP models as well as cluster models.
o distcdf
Improved regularisation algorithm.
Argument 'nr=NULL' is now accepted.
New argument 'delta' allows the result to be interpolated
onto a finer grid.
o collapse.fv
Columns identified by the arguments 'same' and 'different'
may now be absent from some of the 'fv' objects that will be collapsed.
o Kest
When the argument 'domain' is given, the calculation of estimates of K(r)
has changed slightly, to adhere more closely to the description in
the help file.
o reload.or.compute
Now prints a message indicating whether the data were recomputed
or reloaded from file.
New argument 'verbose'.
o update.kppm
New argument 'envir'.
o clusterfit
Minor changes to the argument list.
o mincontrast
Minor changes to the argument list.
o mincontrast
Improved algorithm for handling NA, NaN or infinite values.
o varcount
Argument B has a sensible default.
o pool.envelope
Now uses the value of 'nrank' which was used in the original envelopes.
o Kmulti
New argument 'rmax'.
o Kinhom
No longer issues a warning about changed behaviour in the case where
'lambda' is a fitted model.
o pcfinhom
No longer issues a warning about changed behaviour in the case where
'lambda' is a fitted model.
BUG FIXES
o subfits
The fitted interaction coefficients were garbled.
If 'mfit' is the mppm object and 'a <- subfits(mfit)[[i]]' is one of the
sub-models, then coef(a) was correct, but coef(fitin(a)) was incorrect.
The fitted interaction was shown correctly by printing 'mfit'
but incorrectly by printing 'a'.
Fixed.
o varcount
The result was very inaccurate if the cluster radius was small
compared to the size of the window 'B', due to discretisation error.
Fixed.
o segregation.test
The test statistic was calculated as the mean, rather than the sum,
of discrepancies between probabilities. (The p-value was not affected.)
Fixed.
o Kest
If 'domain' was specified, 'rmax' was ignored.
Fixed.
o edge.Ripley
Value was incorrect for a point lying exactly on a corner.
Fixed.
o edge.Ripley
Crashed when method="interpreted", if a point lay exactly on a corner.
Fixed.
o plot.fv, plot.envelope
Crashed when trying to display a significance band of width zero
around a constant function.
Fixed.
o collapse.fv
Crashed if 'length(same) > 1'.
Fixed.
CHANGES IN spatstat.core VERSION 2.3-0
OVERVIEW
o We thank Chiara Fend for contributions.
o Extensive support for spatial logistic regression models.
o New fitting method in kppm and dppm.
o Transect of an image along a curve.
o Image cross-correlation and cross-covariance.
o Summary method for 'objsurf'.
o Minor bug fixes.
NEW FUNCTIONS
o response
Generic function which extracts the values of the response
in a fitted model. There are methods for lm, glm (which extract the
numeric vector of responses), and ppm, kppm, slrm, lppm and mppm
(which extract the original data point pattern).
o cov.im, cor.im
Correlation or covariance between several pixel images.
o summary.objsurf, print.summary.objsurf
Summary method for 'objsurf'
o residuals.slrm
Residuals for spatial logistic regression models.
o leverage.slrm, influence.slrm, dfbetas.slrm, dffit.slrm
Leverage and influence diagnostics for spatial logistic regression models.
o rhohat.slrm
Method for 'rhohat' for spatial logistic regression models.
o envelope.slrm
Method for 'envelope' for spatial logistic regression models.
o intensity.slrm
Method for 'intensity' for spatial logistic regression models.
o deviance.slrm
Method for 'deviance' for spatial logistic regression models.
o pseudoR2.slrm
Method for 'pseudoR2' for spatial logistic regression models.
o quadrat.test.slrm
Method for 'quadrat.test' for spatial logistic regression models.
o parameters.slrm
Method for 'parameters' for spatial logistic regression models.
o valid.slrm
Method for 'valid' for spatial logistic regression models.
o emend.slrm
Method for 'emend' for spatial logistic regression models.
o roc.slrm
Method for 'roc' for spatial logistic regression models.
o auc.slrm
Method for 'auc' for spatial logistic regression models.
o Window.slrm, as.owin.slrm
Methods for 'Window' and 'as.owin' for spatial logistic regression models.
SIGNIFICANT USER-VISIBLE CHANGES
o kppm, dppm
New option 'method="adapcl"' performs adaptive composite likelihood fitting.
[Contributed by Chiara Fend.]
o transect.im
New argument 'curve' allows the user to specify a curved transect.
BUG FIXES
o clusterfield
Values of the cluster field were slightly incorrect (slightly higher
than the correct values) near the edge of the window,
because an 'edge correction' was mistakenly applied.
Fixed.
o rhohat
The rug plot (produced by plot.rhohat) was incorrect
when rhohat was called with method="piecewise".
Fixed.
o markcrosscorr
Did not recognise the option 'correction="none"'.
Fixed.
o roc.ppp
The default plot of the result of roc.ppp
did not include the diagonal line 'y=x'.
Fixed.
CHANGES IN spatstat.core VERSION 2.2-0
OVERVIEW
o We thank Abdollah Jalilian, Yongtao Guan and Rasmus Waagepetersen
for contributions.
o summary method for spatial logistic regression models
o estimation of the spatial covariance function of a pixel image
o simulation of the product shot noise Cox process.
o extensions to rhohat
NEW FUNCTIONS
o rPSNCP
Generate simulated realisations of the product shot noise Cox process.
Contributed by Abdollah Jalilian, Yongtao Guan and Rasmus Waagepetersen.
o spatcov
Estimate the spatial covariance function of a pixel image.
o summary.slrm, print.summary.slrm
Summary method for spatial logistic regression models
o coef.summary.slrm
Print the fitted coefficients, confidence interval and p-values
for a spatial logistic regression model.
o pairMean
Compute the mean of a specified function of interpoint distance
between random points in a window.
SIGNIFICANT USER-VISIBLE CHANGES
o rhohat
New option (smoother='piecewise') computes a piecewise-constant
estimate of rho(z).
o rhohat
The result now includes the 'average' intensity rho.
o distcdf
Arguments which are NULL will be treated as missing.
o distcdf
New argument 'savedenom'.
CHANGES IN spatstat.core VERSION 2.1-2
OVERVIEW
o Reduced CRAN check time.
CHANGES IN spatstat.core VERSION 2.1-1
OVERVIEW
o Minor bug fix
BUG FIXES
o simulate.kppm
Conditional simulation crashed on rare occasions,
with an error about negative probabilities.
Fixed.
CHANGES IN spatstat.core VERSION 2.1-0
OVERVIEW
o We thank Achmad Choiruddin, Jean-Francois Coeurjolly
and Rasmus Waagepetersen for contributions.
o Conditional simulation in kppm
o Information criteria for model selection in kppm
o Modified handling of covariates in slrm
o densityfun.ppp handles query points outside original window
o Improved output in summary.mppm
o Minor improvements and bug fixes.
NEW FUNCTIONS
o ic
Information criteria for model selection in ppm and kppm.
Kindly contributed by Achmad Choiruddin, Jean-Francois Coeurjolly
and Rasmus Waagepetersen.
SIGNIFICANT USER-VISIBLE CHANGES
o simulate.kppm
Conditional simulation of the model, given a fixed number of points,
is now supported using the new arguments 'n.cond' and 'w.cond'.
o densityfun.ppp
The resulting function can now handle query points which lie
outside the window of the original data,
and has argument 'drop=TRUE' which specifies how to handle them.
o rpoint
New argument 'forcewin' forces the code to use the window 'win'
when 'f' is a pixel image.
o slrm
In the default case (where dataAtPoints is not given)
all spatial covariates, including the spatial coordinates x and y,
are now evaluated at the centre of each pixel. This improves
consistency with other implementations of spatial logistic regression.
o slrm
Silently ignores any arguments '...' that are not recognised by 'as.mask'
o summary.mppm
Improved summary of the dependence of the
interpoint interaction on the covariates.
o pairs.im
New argument 'drop'.
BUG FIXES
o model.matrix.mppm
If the model was fitted using 'gam', the resulting matrix
did not have an 'assign' attribute.
Fixed.
o model.depends
Crashed for models fitted using 'gam'.
Fixed.
o predict.slrm, fitted.slrm
Crashed if the model was fitted using split pixels (argument 'splitby').
Fixed.
o predict.slrm, fitted.slrm
Crashed in some cases when 'window' was given.
Fixed.
o update.slrm
Failed to find covariates that were provided in 'env'.
Fixed.
o cdf.test
Crashed if the covariate was constant.
Fixed.
CHANGES IN spatstat.core VERSION 2.0-0
OVERVIEW
o We thank Tilman Davies, Greg McSwiggan and Suman Rakshit
for contributions.
o We thank Corey Anderson, Michael Chirico, Andy Craig,
Marcelino de la Cruz, Tilman Davies, Pavel Fibich,
Kurt Hornik, Gopalan Nair, Yonatan Rosen and Rasmus Waagepetersen
for contributions.
o Diffusion kernel smoothing.
o More support for spatial logistic regression models.
o predict.mppm now works for multitype point process models.
o Improved handling of 'newdata' in predict.mppm.
o More support for multi-dimensional patterns.
NEW FUNCTIONS
o densityHeat
New generic function for diffusion kernel estimation of intensity
o densityHeat.ppp
Diffusion kernel estimation of intensity for point pattern in 2 dimensions.
This is an alternative to density.ppp.
o intersect.boxx
Compute intersection of boxes in multi-dimensional space
o scale.boxx, scale.ppx
Methods for 'scale' for boxes and patterns in multi-dimensional space
o shift.boxx, shift.ppx
Methods for 'shift' for boxes and patterns in multi-dimensional space
o is.boxx
Determine whether an object is a multidimensional box
o mincontrast
New argument 'action.bad.values' specifies what action is taken
when the summary function produces NA or NaN or infinite values.
SIGNIFICANT USER-VISIBLE CHANGES
o slrm
'step' can now be applied to models fitted using 'slrm'.
o predict.mppm
Now supports multitype point process models.
o predict.mppm
Improved handling of argument 'newdata'
o rotmean
The result now has the same 'unitname' as the input object X.
New argument 'adjust' controls the smoothing bandwidth.
o rlabel
New argument 'group' specifies that the points are divided into
several groups, and that relabelling is applied within each group.
o simulate.ppm
Now recognises the argument 'window' as an alternative to 'w'.
o kppm
Improved numerical robustness.
o Kcross, Gcross, Jcross
Function labels (shown on the plot legend) have been
improved when i = j.
o anova.mppm
Issues a warning when applied to random-effects models
(models fitted using the argument 'random').
BUG FIXES
o Gest
If correction="rs" or correction="km", then both the reduced-sample
(border correction) and Kaplan-Meier corrected estimates were calculated.
[Spotted by Gopalan Nair.]
Fixed.
o rMatClust, rThomas, rCauchy, rVarGamma
If the fitted model was effectively a Poisson process,
the result did not have attributes 'Lambda' and 'parents'
even when the user requested them.
Fixed.
o model.matrix.mppm
Crashed with random-effects models.
Fixed.
o anova.mppm
Crashed with random-effects models.
Fixed.
o simulate.rhohat
Crashed when applied to rhohat objects computed from data
on a linear network.
Fixed.
o objsurf.kppm
Crashed if the model was fitted by Palm likelihood (method="palm")
or second order composite likelihood (method="clik2").
Fixed.
CHANGES IN spatstat.core VERSION 1.65-11
OVERVIEW
o Internal tweaks.
CHANGES IN spatstat.core VERSION 1.65-10
OVERVIEW
o Minor corrections to documentation.
CHANGES IN spatstat.core VERSION 1.65-9
OVERVIEW
o We thank Ian Buller for a suggestion.
o weights permitted in density calculation for line segments.
SIGNIFICANT USER-VISIBLE CHANGES
o density.psp
New argument 'weights'.
CHANGES IN spatstat.core VERSION 1.65-8
OVERVIEW
o Minor changes to appease the compiler.
CHANGES IN spatstat.core VERSION 1.65-7
OVERVIEW
o We thank Michael Chirico for a contribution.
o Minor changes to appease the compiler.
CHANGES IN spatstat.core VERSION 1.65-6
OVERVIEW
o We thank Tilman Davies and Pavel Fibich for contributions.
o Important bug fix in simulation of log-Gaussian Cox processes.
o Increased speed for large datasets.
o variance calculations handle larger datasets.
SIGNIFICANT USER-VISIBLE CHANGES
o vcov.ppm, summary.ppm
Variance calculations now handle larger datasets
(using sparse arrays).
o rSSI
Accelerated.
o overall speed
Changes have been made to the internal code of spatstat
which should accelerate computations involving large datasets.
o localpcf, localpcfinhom
New argument 'rvalue'.
BUG FIXES
o rLGCP, simulate.kppm
Simulation results for log-Gaussian Cox processes were incorrect
unless the pixel dimensions and pixel spacings were identical
on the horizontal and vertical axes. (If pixel dimensions were not
specified, then the results were incorrect whenever the Frame of the
simulation window was not a square.)
[Spotted by Tilman Davies.]
Fixed.
o Vmark
Crashed if normalise=TRUE when there was only one column of marks.
(Spotted by Pavel Fibich.)
Fixed.
o nnclean
Crashed if k >= npoints(X).
Fixed.
o print.ppm
Crashed sometimes when applied to the result of subfits().
Fixed.
CHANGES IN spatstat.core VERSION 1.65-5
OVERVIEW
o Minor changes required by CRAN.
CHANGES IN spatstat.core VERSION 1.65-1
OVERVIEW
o Added NEWS file.
CHANGES IN spatstat.core VERSION 1.65-0
OVERVIEW
o Package initialised at version 1.65-0
SIGNIFICANT USER-VISIBLE CHANGES
o spatstat.core
The package 'spatstat.core' has been created from a subset
of the code in the original 'spatstat' package version 1.65-0.
It contains the core functionality for statistical analysis of
spatial data. For an overview, see help("spatstat.core-package")
o Execution
The 'spatstat.core' package is slightly faster than the corresponding
code in the 'spatstat' package, because the procedure for calling
internal C functions has been streamlined.