Local Empirical Bayes estimator
The function computes local empirical Bayes estimates for rates "shrunk" to a neighbourhood mean for neighbourhoods given by the
nb neighbourhood list.
EBlocal(ri, ni, nb, zero.policy = NULL, spChk = NULL, geoda=FALSE)
- a numeric vector of counts of cases the same length as the neighbours list in nb
- a numeric vector of populations at risk the same length as the neighbours list in nb
nbobject of neighbour relationships
- default NULL, use global option value; if TRUE assign zero to the lagged value of zones without neighbours, if FALSE assign NA
- should the data vector names be checked against the spatial objects for identity integrity, TRUE, or FALSE, default NULL to use
- default=FALSE, following Marshall's algorithm as interpreted by Bailey and Gatrell, pp. 305-307, and exercise 8.2, pp. 328-330 for the definition of phi; TRUE for the definition of phi used in GeoDa (see discussion on OpenSpace mailing list June 2003: http://agec221.agecon.uiuc.edu/pipermail/openspace/2003-June/thread.html)
Details of the implementation are to be found in Marshall, p. 286, and Bailey and Gatrell p. 307 and exercise 8.2, pp. 328--330. The example results do not fully correspond to the sources because of slightly differing neighbourhoods, but are generally close.
A data frame with two columns:and a
parametersattribute list with components:
Marshall R M (1991) Mapping disease and mortality rates using Empirical Bayes Estimators, Applied Statistics, 40, 283--294; Bailey T, Gatrell A (1995) Interactive Spatial Data Analysis, Harlow: Longman, pp. 303--306.
example(auckland) res <- EBlocal(auckland$M77_85, 9*auckland$Und5_81, auckland.nb) brks <- c(-Inf,2,2.5,3,3.5,Inf) cols <- grey(6:2/7) plot(auckland, col=cols[findInterval(res$est*1000, brks, all.inside=TRUE)]) legend("bottomleft", fill=cols, legend=leglabs(brks), bty="n") title(main="Local moment estimator of infant mortality per 1000 per year")