RELEASE NOTES 

		spatstat 1.6-7

		25 May 2005

OVERVIEW

	Diagnostic plots for a fitted point process model,
	proposed in Baddeley et al (2005), are implemented. 

	Various minor improvements have also been made.

NEW FUNCTIONS

	demo(diagnose)
		A demonstration of the new diagnostics.

	diagnose.ppm
	lurking
	qqplot.ppm
		Generate diagnostic plots for a fitted point process model.

	residuals.ppm
	eem
		Calculate residuals for a fitted point process model
		(which are plotted by diagnose.ppm and qqplot.ppm)

NEW DATASETS

	residualspaper
		Contains all data analysed in Baddeley et al (2005) 
		together with R code to produce the Figures in the paper.


IMPROVEMENTS/ENHANCEMENTS

	1. ppm, quadscheme
		Some potential sources of error in the quadrature scheme
		have been removed.

	2. nearest.raster.point
		has a new argument 'indices'

	3. as.mask
		conversion of polygons to binary masks
		is now much faster. 

	4. 'copper' dataset
		copper$SouthDistance() now runs much faster.

	5. applynbd
		Arguments to the function FUN have been changed
		to make applynbd easier to use.

	6. error checks have been added to various pieces of internal code,
	   making the package more robust against errors.


COMPATIBILITY

	No compatibility issues regarding data.

	'applynbd' has been modified.


BUGS

	[1] ppm, quadscheme
		An obscure warning was generated if the data point pattern
		was in a non-rectangular window. 
		Fixed.

	[2] erode.owin
		the value of erode.owin(W, r) was partially incorrect 
		in the case where the window W was a mask.
		The xrange and yrange of the result were incorrect.
		Fixed.

REFERENCES
	A. Baddeley, R. Turner, J. Moller and M. Hazelton (2005)
	Residual analysis for spatial point processes.
	Journal of the Royal Statistical Society, series B.
	To appear.
	(Electronic publication date: June 2005).