[Vegan-commits] r1558 - in pkg/vegan: R inst man tests/Examples
noreply at r-forge.r-project.org
noreply at r-forge.r-project.org
Wed Mar 30 15:42:45 CEST 2011
Author: gsimpson
Date: 2011-03-30 15:42:45 +0200 (Wed, 30 Mar 2011)
New Revision: 1558
Added:
pkg/vegan/R/tolerance.R
pkg/vegan/R/tolerance.cca.R
pkg/vegan/man/tolerance.Rd
Modified:
pkg/vegan/inst/ChangeLog
pkg/vegan/tests/Examples/vegan-Ex.Rout.save
Log:
Adds tolerance and cca method for finding species tolerances and sample heterogeneities from cca() models.
Added: pkg/vegan/R/tolerance.R
===================================================================
--- pkg/vegan/R/tolerance.R (rev 0)
+++ pkg/vegan/R/tolerance.R 2011-03-30 13:42:45 UTC (rev 1558)
@@ -0,0 +1,8 @@
+##' S3 generic for function to compute tolerances
+##'
+##' Brought this in here from analogue because of tolerance.cca
+##'
+##' @param x an R object
+##' @param ... arguments passed to other methods
+`tolerance` <- function(x, ...)
+ UseMethod("tolerance")
Added: pkg/vegan/R/tolerance.cca.R
===================================================================
--- pkg/vegan/R/tolerance.cca.R (rev 0)
+++ pkg/vegan/R/tolerance.cca.R 2011-03-30 13:42:45 UTC (rev 1558)
@@ -0,0 +1,94 @@
+##' Species tolerances and sample heterogeneities
+##'
+##' Function to compute species tolerances and site heterogeneity measures
+##' from unimodal ordinations (CCA & CA). Implements Eq 6.47 and 6.48 from
+##' the Canoco 4.5 Reference Manual (pages 178-179).
+##'
+##' @param x object of class \code{"cca"}.
+##' @param choices numeric; which ordination axes to compute
+##' tolerances and heterogeneities for. Defaults to axes 1 and 2.
+##' @param which character; one of \code{"species"} or \code{"sites"},
+##' indicating whether species tolerances or sample heterogeneities
+##' respectively are computed.
+##' @param scaling numeric; the ordination scaling to use.
+##' @param useN2 logical; should the bias in the tolerances /
+##' heterogeneities be reduced via scaling by Hill's N2?
+##' @param ... arguments passed to other methods
+##' @return matrix of tolerances/heterogeneities with some additional
+##' attributes.
+##' @author Gavin Simpson \email{gavin.simpson AT ucl.ac.uk}
+##' @examples
+##' data(dune)
+##' data(dune.env)
+##' mod <- cca(dune ~ ., data = dune.env)
+##' tolerance.cca(mod)
+##'
+tolerance.cca <- function(x, choices = 1:2,
+ which = c("species","sites"),
+ scaling = 2, useN2 = FALSE, ...) {
+ if(inherits(x, "rda"))
+ stop("Tolerances only available for unimodal ordinations.")
+ if(missing(which))
+ which <- "species"
+ ## reconstruct species/response matrix Y - up to machine precision!
+ partialFit <- ifelse(is.null(x$pCCA$Fit), 0, x$pCCA$Fit)
+ Y <- ((partialFit + x$CCA$Xbar) * sqrt(x$rowsum %o% x$colsum) +
+ x$rowsum %o% x$colsum) * x$grand.total
+ which <- match.arg(which)
+ siteScrTypes <- if(is.null(x$CCA)){ "sites" } else {"lc"}
+ scrs <- scores(x, display = c(siteScrTypes,"species"),
+ choices = choices, scaling = scaling)
+ ## compute N2 if useN2 == TRUE & only if
+ doN2 <- isTRUE(useN2) && ((which == "species" && abs(scaling) == 2) ||
+ (which == "sites" && abs(scaling) == 1))
+
+ ## this gives the x_i - u_k on axis j
+ ## outer(scrs$sites, scrs$species, "-")[,2,,j]
+ siteScrs <- which(names(scrs) %in% c("sites","constraints"))
+ xiuk <- outer(scrs[[siteScrs]], scrs$species, "-")
+ if(isTRUE(all.equal(which, "sites"))) {
+ ## need to permute the array as rowSums has different idea of what rows
+ ## are that doesn't correspond to colSums. So flip dimensions 1 and 2
+ ## with aperm and use colSums.
+ res <- sqrt(sweep(colSums(aperm(sweep(xiuk[ , 2, , choices]^2, c(1:2),
+ data.matrix(Y), "*"),
+ c(2,1,3))),
+ 1, rowSums(Y), "/"))
+ if(doN2) {
+ tot <- rowSums(Y)
+ y <- sweep(Y, 1, tot, "/")^2
+ N2 <- 1 / rowSums(y, na.rm = TRUE) ## 1/H
+ res <- sweep(res, 1, sqrt(1 - (1/N2)), "/")
+ }
+ } else {
+ res <- sqrt(sweep(colSums(sweep(xiuk[ , 2, , choices]^2, c(1:2),
+ data.matrix(Y), "*")),
+ 1, colSums(Y), "/"))
+ if(doN2) {
+ tot <- colSums(Y)
+ y <- sweep(Y, 2, tot, "/")^2
+ N2 <- 1 / colSums(y, na.rm = TRUE) ## 1/H
+ res <- sweep(res, 1, sqrt(1 - (1/N2)), "/")
+ }
+ }
+ class(res) <- c("tolerance.cca","tolerance","matrix")
+ attr(res, "which") <- which
+ attr(res, "scaling") <- scaling
+ attr(res, "N2") <- NULL
+ if(doN2)
+ attr(res, "N2") <- N2
+ attr(res, "model") <- deparse(substitute(mod))
+ return(res)
+}
+
+`print.tolerance.cca` <- function(x, ...) {
+ cat("\n")
+ msg <- ifelse(attr(x, "which") == "species", "Species Tolerances",
+ "Sample Heterogeneities")
+ writeLines(strwrap(msg, prefix = "\t"), sep = "\n\n")
+ msg <- paste("Scaling:", attr(x, "scaling"))
+ writeLines(strwrap(msg), sep = "\n\n")
+ attr(x, "model") <- attr(x, "scaling") <- attr(x, "which") <- NULL
+ print(unclass(x), ...)
+ cat("\n")
+}
Modified: pkg/vegan/inst/ChangeLog
===================================================================
--- pkg/vegan/inst/ChangeLog 2011-03-28 19:16:05 UTC (rev 1557)
+++ pkg/vegan/inst/ChangeLog 2011-03-30 13:42:45 UTC (rev 1558)
@@ -23,10 +23,14 @@
a Condition in updated models. Added a regression test that checks
that statistics and residual df match.
+ * tolerance: new function to compute species tolerances and sample
+ heterogeneities as Canoco does. Includes a method for objects of
+ class "cca".
+
Version 1.18-25 (closed March 23, 2011)
* ordilabel: gained argument 'xpd' to draw labels outside the plot
- region.
+ region.
* ordisurf: got a formula interface as an alternative to define
the model. Also now accepts `gam()` argument `select` to add an
Added: pkg/vegan/man/tolerance.Rd
===================================================================
--- pkg/vegan/man/tolerance.Rd (rev 0)
+++ pkg/vegan/man/tolerance.Rd 2011-03-30 13:42:45 UTC (rev 1558)
@@ -0,0 +1,47 @@
+\name{tolerance}
+\alias{tolerance}
+\alias{tolerance.cca}
+\alias{print.tolerance.cca}
+\title{Species tolerances and sample heterogeneities}
+\usage{
+tolerance(x, \dots)
+
+\method{tolerance}{cca}(x, choices = 1:2, which = c("species","sites"),
+ scaling = 2, useN2 = FALSE, \dots)
+}
+\description{
+ Species tolerances and sample heterogeneities.
+}
+\details{
+ Function to compute species tolerances and site heterogeneity measures
+ from unimodal ordinations (CCA & CA). Implements Eq 6.47 and 6.48 from
+ the Canoco 4.5 Reference Manual (pages 178-179).
+}
+\value{
+ Matrix of tolerances/heterogeneities with some additional
+ attributes.
+}
+\author{Gavin L. Simpson}
+\arguments{
+ \item{x}{object of class \code{"cca"}.}
+ \item{choices}{numeric; which ordination axes to compute
+ tolerances and heterogeneities for. Defaults to axes 1 and 2.}
+ \item{which}{character; one of \code{"species"} or \code{"sites"},
+ indicating whether species tolerances or sample heterogeneities
+ respectively are computed.}
+ \item{scaling}{numeric; the ordination scaling to use.}
+ \item{useN2}{logical; should the bias in the tolerances /
+ heterogeneities be reduced via scaling by Hill's N2?}
+ \item{\dots}{arguments passed to other methods.}
+}
+\examples{
+data(dune)
+data(dune.env)
+mod <- cca(dune ~ ., data = dune.env)
+
+## defaults to species tolerances
+tolerance.cca(mod)
+
+## sample heterogeneities for CCA axes 1:6
+tolerance.cca(mod, which = "sites", choices = 1:6)
+}
Modified: pkg/vegan/tests/Examples/vegan-Ex.Rout.save
===================================================================
--- pkg/vegan/tests/Examples/vegan-Ex.Rout.save 2011-03-28 19:16:05 UTC (rev 1557)
+++ pkg/vegan/tests/Examples/vegan-Ex.Rout.save 2011-03-30 13:42:45 UTC (rev 1558)
@@ -1,8 +1,8 @@
-R version 2.12.2 (2011-02-25)
+R version 2.13.0 alpha (2011-03-28 r55109)
Copyright (C) 2011 The R Foundation for Statistical Computing
ISBN 3-900051-07-0
-Platform: x86_64-apple-darwin9.8.0/x86_64 (64-bit)
+Platform: x86_64-unknown-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
@@ -385,8 +385,8 @@
Inertia is mean squared contingency coefficient
Eigenvalues for constrained axes:
- CCA1 CCA2 CCA3
-0.4187 0.1330 0.0766
+ CCA1 CCA2 CCA3
+0.41868 0.13304 0.07659
Eigenvalues for unconstrained axes:
CA1 CA2 CA3 CA4 CA5 CA6 CA7 CA8
@@ -845,31 +845,31 @@
Influence measures of
lm(formula = wa ~ . - 1, data = as.data.frame(X)) :
- dfb.Al dfb.P dfb.K CCA1 CCA2 CCA3 cov.r CCA1.1
-18 -0.251387 0.00976 -0.06310 0.2740 0.1806 -0.118754 0.0265 7.38e-03
-15 0.099858 0.13864 -0.11781 -0.1654 -0.0935 0.006898 0.0319 2.86e-03
-24 -0.003448 -0.44078 0.20788 -0.4824 -0.1750 -0.260788 0.0307 2.33e-02
-27 0.071682 -0.01707 -0.03516 -0.1018 -0.1676 0.022271 0.0406 1.13e-03
-23 -0.116533 0.06900 -0.02545 0.1441 0.2918 -0.220457 0.0355 2.23e-03
-19 -0.007394 -0.01169 0.01080 0.0136 -0.2318 -0.000417 0.0359 2.02e-05
-22 0.150916 0.14845 -0.13091 -0.2047 0.3815 0.168914 0.0376 4.50e-03
-16 0.107456 0.17900 -0.09917 -0.2120 0.2250 0.194432 0.0338 4.75e-03
-28 0.332161 -0.34398 -0.05414 -0.6774 0.0742 0.620990 0.0364 4.65e-02
-13 0.366880 -1.00834 1.23685 1.3392 0.4102 0.277067 0.1124 1.89e-01
-14 0.024147 0.02512 -0.01161 -0.0361 0.1491 0.053638 0.0355 1.42e-04
-20 0.000747 -0.00560 0.00205 -0.0066 0.2935 -0.190351 0.0368 4.77e-06
-25 0.166736 -0.11049 0.09341 -0.2095 -0.1627 -0.070753 0.0346 4.66e-03
-7 -0.397145 0.15747 0.15662 -0.5912 0.5842 -0.838287 0.0327 3.51e-02
-5 -0.279996 -0.09119 -0.35616 0.7358 0.3694 -0.326563 0.0281 5.18e-02
-6 0.003191 -0.00168 -0.01550 0.0259 0.3447 0.201072 0.0400 7.34e-05
-3 -0.302851 -0.07889 0.25932 -0.4196 -0.2766 0.536017 0.0386 1.85e-02
-4 -0.058151 -0.02719 0.00870 -0.0664 0.8199 0.131003 0.0486 4.83e-04
-2 0.020380 0.00416 -0.00373 0.0206 -0.4158 -0.160401 0.0395 4.62e-05
-9 0.074217 0.09551 -0.10857 0.1271 -0.3481 0.644579 0.0383 1.75e-03
-12 -0.097825 -0.20830 0.04637 0.2864 -0.6601 0.270324 0.0280 8.19e-03
-10 0.149178 0.66594 -0.12975 0.8935 -0.2510 0.000571 0.0118 5.90e-02
-11 0.014687 0.00691 0.00105 0.0191 0.1838 -0.301086 0.0377 4.00e-05
-21 0.148213 0.15461 -0.02915 -0.2531 -0.1892 -0.318491 0.0361 6.81e-03
+ dfb.Al dfb.P dfb.K CCA1 CCA2 CCA3 cov.r CCA1.1
+18 -0.251387 0.00976 -0.06310 0.27401 0.1806 -0.118754 0.0265 7.38e-03
+15 0.099858 0.13864 -0.11781 -0.16542 -0.0935 0.006898 0.0319 2.86e-03
+24 -0.003448 -0.44078 0.20788 -0.48239 -0.1750 -0.260788 0.0307 2.33e-02
+27 0.071682 -0.01707 -0.03516 -0.10185 -0.1676 0.022271 0.0406 1.13e-03
+23 -0.116533 0.06900 -0.02545 0.14407 0.2918 -0.220457 0.0355 2.23e-03
+19 -0.007394 -0.01169 0.01080 0.01360 -0.2318 -0.000417 0.0359 2.02e-05
+22 0.150916 0.14845 -0.13091 -0.20466 0.3815 0.168914 0.0376 4.50e-03
+16 0.107456 0.17900 -0.09917 -0.21196 0.2250 0.194432 0.0338 4.75e-03
+28 0.332161 -0.34398 -0.05414 -0.67745 0.0742 0.620990 0.0364 4.65e-02
+13 0.366880 -1.00834 1.23685 1.33919 0.4102 0.277067 0.1124 1.89e-01
+14 0.024147 0.02512 -0.01161 -0.03608 0.1491 0.053638 0.0355 1.42e-04
+20 0.000747 -0.00560 0.00205 -0.00661 0.2935 -0.190351 0.0368 4.77e-06
+25 0.166736 -0.11049 0.09341 -0.20954 -0.1627 -0.070753 0.0346 4.66e-03
+7 -0.397145 0.15747 0.15662 -0.59116 0.5842 -0.838287 0.0327 3.51e-02
+5 -0.279996 -0.09119 -0.35616 0.73579 0.3694 -0.326563 0.0281 5.18e-02
+6 0.003191 -0.00168 -0.01550 0.02590 0.3447 0.201072 0.0400 7.34e-05
+3 -0.302851 -0.07889 0.25932 -0.41958 -0.2766 0.536017 0.0386 1.85e-02
+4 -0.058151 -0.02719 0.00870 -0.06644 0.8199 0.131003 0.0486 4.83e-04
+2 0.020380 0.00416 -0.00373 0.02055 -0.4158 -0.160401 0.0395 4.62e-05
+9 0.074217 0.09551 -0.10857 0.12712 -0.3481 0.644579 0.0383 1.75e-03
+12 -0.097825 -0.20830 0.04637 0.28644 -0.6601 0.270324 0.0280 8.19e-03
+10 0.149178 0.66594 -0.12975 0.89348 -0.2510 0.000571 0.0118 5.90e-02
+11 0.014687 0.00691 0.00105 0.01913 0.1838 -0.301086 0.0377 4.00e-05
+21 0.148213 0.15461 -0.02915 -0.25306 -0.1892 -0.318491 0.0361 6.81e-03
CCA2.1 CCA3.1 hat inf
18 0.003207 1.39e-03 0.0321
15 0.000915 4.98e-06 0.0295
@@ -987,27 +987,27 @@
19 0.5548077 0.082361157 0.11966159 0.8147968 0.51929869 0.36429493 0.29826049
12 0.6932541 0.100954127 0.13849854 0.9079979 0.20078932 0.08041977 0.21008725
7 0.8925059 0.024070054 0.32489503 0.9171688 0.48010987 0.07094548 0.56496165
- Poatri Chealb Elyrep Sagpro Plalan Agrsto Lolper
-2 0.8288385 0.04386656 0.4407282 0.3302063 0.40700777 0.39501120 0.8272395
-13 0.7993754 0.12254774 0.3511708 0.5131337 0.18153869 0.68239707 0.5714581
-4 0.8197302 0.05797091 0.4399661 0.4191908 0.25797285 0.51198853 0.7197924
-16 0.6071083 0.05624699 0.1832397 0.3480368 0.07269979 0.87877202 0.3561752
-6 0.7782619 0.02125637 0.3138879 0.2539380 0.58765018 0.26299306 0.8000021
-1 0.8826329 0.02513228 0.4667439 0.3371121 0.40103107 0.38333415 0.9226190
-8 0.7101299 0.06327845 0.3046956 0.4009544 0.20596764 0.66906674 0.5403355
-5 0.8094632 0.02643474 0.3575948 0.2612828 0.52628928 0.27622698 0.8380779
-17 0.5036834 0.00771605 0.1929470 0.3292030 0.59641331 0.07330247 0.5858415
-15 0.5263520 0.03560905 0.1462975 0.3151199 0.13523214 0.79412733 0.3689922
-10 0.7543592 0.02568664 0.3736128 0.2732735 0.52588347 0.26902092 0.8102783
-11 0.6404351 0.02123473 0.2884798 0.3673397 0.47012501 0.31656550 0.7180948
-9 0.8247374 0.06987928 0.3523460 0.4531178 0.25274756 0.59744543 0.6874068
-18 0.5859071 0.01464043 0.2651538 0.3154533 0.45087176 0.34451209 0.7124388
-3 0.8383185 0.06533864 0.4137888 0.4204104 0.27933493 0.52738394 0.7205525
-20 0.4523029 0.03762374 0.1168700 0.3105433 0.13059496 0.76675441 0.3262685
-14 0.5090703 0.04299059 0.1428372 0.2528665 0.14342002 0.76284476 0.3356311
-19 0.3605827 0.01959125 0.1422725 0.4798245 0.40784415 0.25952255 0.4289185
-12 0.8199960 0.10354334 0.3354080 0.5122033 0.22110550 0.66278454 0.5875943
-7 0.8018775 0.03846771 0.3586644 0.2954682 0.51905808 0.29412293 0.8053380
+ Poatri Chealb Elyrep Sagpro Plalan Agrsto Lolper
+2 0.8288385 0.043866562 0.4407282 0.3302063 0.40700777 0.39501120 0.8272395
+13 0.7993754 0.122547745 0.3511708 0.5131337 0.18153869 0.68239707 0.5714581
+4 0.8197302 0.057970906 0.4399661 0.4191908 0.25797285 0.51198853 0.7197924
+16 0.6071083 0.056246994 0.1832397 0.3480368 0.07269979 0.87877202 0.3561752
+6 0.7782619 0.021256367 0.3138879 0.2539380 0.58765018 0.26299306 0.8000021
+1 0.8826329 0.025132275 0.4667439 0.3371121 0.40103107 0.38333415 0.9226190
+8 0.7101299 0.063278453 0.3046956 0.4009544 0.20596764 0.66906674 0.5403355
+5 0.8094632 0.026434737 0.3575948 0.2612828 0.52628928 0.27622698 0.8380779
+17 0.5036834 0.007716049 0.1929470 0.3292030 0.59641331 0.07330247 0.5858415
+15 0.5263520 0.035609053 0.1462975 0.3151199 0.13523214 0.79412733 0.3689922
+10 0.7543592 0.025686639 0.3736128 0.2732735 0.52588347 0.26902092 0.8102783
+11 0.6404351 0.021234732 0.2884798 0.3673397 0.47012501 0.31656550 0.7180948
+9 0.8247374 0.069879277 0.3523460 0.4531178 0.25274756 0.59744543 0.6874068
+18 0.5859071 0.014640428 0.2651538 0.3154533 0.45087176 0.34451209 0.7124388
+3 0.8383185 0.065338638 0.4137888 0.4204104 0.27933493 0.52738394 0.7205525
+20 0.4523029 0.037623741 0.1168700 0.3105433 0.13059496 0.76675441 0.3262685
+14 0.5090703 0.042990591 0.1428372 0.2528665 0.14342002 0.76284476 0.3356311
+19 0.3605827 0.019591245 0.1422725 0.4798245 0.40784415 0.25952255 0.4289185
+12 0.8199960 0.103543341 0.3354080 0.5122033 0.22110550 0.66278454 0.5875943
+7 0.8018775 0.038467708 0.3586644 0.2954682 0.51905808 0.29412293 0.8053380
Alogen Brohor
2 0.4718807 0.42000984
13 0.6404427 0.24942466
@@ -1822,10 +1822,10 @@
Detrended correspondence analysis with 26 segments.
Rescaling of axes with 4 iterations.
- DCA1 DCA2 DCA3 DCA4
-Eigenvalues 0.5235 0.3253 0.2001 0.19176
-Decorana values 0.5249 0.1572 0.0967 0.06075
-Axis lengths 2.8161 2.2054 1.5465 1.64864
+ DCA1 DCA2 DCA3 DCA4
+Eigenvalues 0.5235 0.3253 0.20010 0.19176
+Decorana values 0.5249 0.1572 0.09669 0.06075
+Axis lengths 2.8161 2.2054 1.54650 1.64864
> summary(vare.dca)
@@ -1835,10 +1835,10 @@
Detrended correspondence analysis with 26 segments.
Rescaling of axes with 4 iterations.
- DCA1 DCA2 DCA3 DCA4
-Eigenvalues 0.5235 0.3253 0.2001 0.19176
-Decorana values 0.5249 0.1572 0.0967 0.06075
-Axis lengths 2.8161 2.2054 1.5465 1.64864
+ DCA1 DCA2 DCA3 DCA4
+Eigenvalues 0.5235 0.3253 0.20010 0.19176
+Decorana values 0.5249 0.1572 0.09669 0.06075
+Axis lengths 2.8161 2.2054 1.54650 1.64864
Species scores:
@@ -2141,8 +2141,8 @@
Inertia is mean squared contingency coefficient
Eigenvalues for constrained axes:
- CCA1 CCA2 CCA3
-0.4187 0.1330 0.0766
+ CCA1 CCA2 CCA3
+0.41868 0.13304 0.07659
Eigenvalues for unconstrained axes:
CA1 CA2 CA3 CA4 CA5 CA6 CA7 CA8
@@ -2414,7 +2414,7 @@
Square root transformation
Wisconsin double standardization
Run 0 stress 18.44915
-Run 1 stress 18.45800
+Run 1 stress 18.458
... procrustes: rmse 0.05246287 max resid 0.1748373
Run 2 stress 24.19514
Run 3 stress 19.69805
@@ -2430,7 +2430,7 @@
Run 11 stress 18.52397
Run 12 stress 21.37384
Run 13 stress 19.5049
-Run 14 stress 21.67150
+Run 14 stress 21.6715
Run 15 stress 22.65719
Run 16 stress 21.0961
Run 17 stress 18.25659
@@ -2550,12 +2550,12 @@
4.885798 2.932690 32.022923
Frequencies by Octave
- 0 1 2 3 4 5 6
-Observed 9.500000 16.00000 18.00000 19.00000 30.00000 35.00000 31.00000
-Fitted 7.994154 13.31175 19.73342 26.04200 30.59502 31.99865 29.79321
- 7 8 9 10 11
-Observed 26.50000 18.00000 13.00000 7.000000 2.0000
-Fitted 24.69491 18.22226 11.97021 7.000122 3.6443
+ 0 1 2 3 4 5 6 7
+Observed 9.500000 16.00000 18.00000 19.000 30.00000 35.00000 31.00000 26.50000
+Fitted 7.994154 13.31175 19.73342 26.042 30.59502 31.99865 29.79321 24.69491
+ 8 9 10 11
+Observed 18.00000 13.00000 7.000000 2.0000
+Fitted 18.22226 11.97021 7.000122 3.6443
> mod.ll
@@ -2570,9 +2570,9 @@
0 1 2 3 4 5 6 7
Observed 9.50000 16.00000 18.00000 19.00000 30.00000 35.00000 31.00000 26.50000
Fitted 9.52392 15.85637 23.13724 29.58961 33.16552 32.58022 28.05054 21.16645
- 8 9 10 11
-Observed 18.00000 13.000000 7.000000 2.000000
-Fitted 13.99829 8.113746 4.121808 1.835160
+ 8 9 10 11
+Observed 18.00000 13.000000 7.000000 2.00000
+Fitted 13.99829 8.113746 4.121808 1.83516
> plot(mod.oct)
> lines(mod.ll, line.col="blue3") # Different
@@ -2841,7 +2841,7 @@
Wisconsin double standardization
Loading required package: MASS
Run 0 stress 18.44915
-Run 1 stress 18.45800
+Run 1 stress 18.458
... procrustes: rmse 0.05246287 max resid 0.1748373
Run 2 stress 24.19514
Run 3 stress 19.69805
@@ -2857,7 +2857,7 @@
Run 11 stress 18.52397
Run 12 stress 21.37384
Run 13 stress 19.5049
-Run 14 stress 21.67150
+Run 14 stress 21.6715
Run 15 stress 22.65719
Run 16 stress 21.0961
Run 17 stress 18.25659
@@ -2934,22 +2934,22 @@
Coefficients:
Estimate Std. Error
-hump 5.3767e+02 3.3533e+01
-scale 1.8393e+01 1.7634e+00
-alpha 9.2294e+06 3.4044e+07
+hump 5.3766e+02 3.3528e+01
+scale 1.8394e+01 1.7472e+00
+alpha 2.4233e+06 7.7206e+06
Dispersion parameter for poisson family taken to be 1
-Deviance 41.44821 with 11 residual degrees of freedom
-AIC: 96.37774 BIC: 98.29492
+Deviance 41.44826 with 11 residual degrees of freedom
+AIC: 96.3778 BIC: 98.29497
Correlation of Coefficients:
hump scale
-scale -0.20
-alpha -0.05 -0.14
+scale -0.21
+alpha -0.02 0.01
Diagnostics from nlm:
-Number of iterations: 87, code: 5
+Number of iterations: 79, code: 2
> plot(sol)
> # confint is in MASS, and impicitly calls profile.humpfit.
> # Parameter 3 (alpha) is too extreme for profile and confint, and we
@@ -2959,8 +2959,8 @@
> confint(sol, parm=c(1,2))
Waiting for profiling to be done...
2.5 % 97.5 %
-hump 494.14239 607.25824
-scale 15.17635 22.02856
+hump 494.14179 607.25654
+scale 15.17642 22.02868
>
>
>
@@ -3110,21 +3110,21 @@
> kendall.post(mite.hel, group=group, mult="holm", nperm=99)
$A_posteriori_tests_Group
$A_posteriori_tests_Group[[1]]
- Brachy PHTH RARD SSTR Protopl MEGR
-Spearman.mean 0.1851177 0.4258111 0.3590580 0.2505486 0.1802160 0.2833298
-W.per.species 0.2190711 0.4497357 0.3857640 0.2817757 0.2143736 0.3131911
-Prob 0.0100000 0.0100000 0.0100000 0.0100000 0.0400000 0.0100000
-Corrected prob 0.3500000 0.3500000 0.3500000 0.3500000 0.3500000 0.3500000
+ Brachy PHTH RARD SSTR Protopl MEGR
+Spearman.mean 0.1851177 0.4258111 0.359058 0.2505486 0.1802160 0.2833298
+W.per.species 0.2190711 0.4497357 0.385764 0.2817757 0.2143736 0.3131911
+Prob 0.0100000 0.0100000 0.010000 0.0100000 0.0400000 0.0100000
+Corrected prob 0.3500000 0.3500000 0.350000 0.3500000 0.3500000 0.3500000
MPRO HMIN HMIN2 NPRA TVEL ONOV
Spearman.mean 0.09248024 0.2444656 0.4138494 0.1263751 0.4177343 0.3301159
W.per.species 0.13029357 0.2759462 0.4382723 0.1627761 0.4419954 0.3580278
Prob 0.08000000 0.0100000 0.0100000 0.0400000 0.0100000 0.0100000
Corrected prob 0.35000000 0.3500000 0.3500000 0.3500000 0.3500000 0.3500000
- SUCT Oribatl1 PWIL Galumna1 Stgncrs2 HRUF
-Spearman.mean 0.2185421 0.4212160 0.2574779 0.4180699 0.3623428 0.1250230
-W.per.species 0.2511028 0.4453320 0.2884163 0.4423170 0.3889118 0.1614804
-Prob 0.0100000 0.0100000 0.0100000 0.0100000 0.0100000 0.0500000
-Corrected prob 0.3500000 0.3500000 0.3500000 0.3500000 0.3500000 0.3500000
+ SUCT Oribatl1 PWIL Galumna1 Stgncrs2 HRUF
+Spearman.mean 0.2185421 0.421216 0.2574779 0.4180699 0.3623428 0.1250230
+W.per.species 0.2511028 0.445332 0.2884163 0.4423170 0.3889118 0.1614804
+Prob 0.0100000 0.010000 0.0100000 0.0100000 0.0100000 0.0500000
+Corrected prob 0.3500000 0.350000 0.3500000 0.3500000 0.3500000 0.3500000
PPEL SLAT FSET Lepidzts Eupelops Miniglmn
Spearman.mean 0.2188216 0.3016159 0.4217606 0.2577037 0.1108022 0.2301430
W.per.species 0.2513707 0.3307153 0.4458539 0.2886327 0.1478521 0.2622203
@@ -3408,7 +3408,7 @@
> # NMDS
> sol <- metaMDS(dune)
Run 0 stress 12.05894
-Run 1 stress 18.21960
+Run 1 stress 18.2196
Run 2 stress 18.97837
Run 3 stress 18.57544
Run 4 stress 19.42521
@@ -3448,7 +3448,7 @@
Run 2 stress 18.60079
Run 3 stress 11.97273
... New best solution
-... procrustes: rmse 0.0001281550 max resid 0.0004408931
+... procrustes: rmse 0.000128155 max resid 0.0004408931
*** Solution reached
>
@@ -3613,7 +3613,7 @@
Run 4 stress 18.57545
Run 5 stress 20.78037
Run 6 stress 12.04546
-... procrustes: rmse 3.743805e-05 max resid 0.0001122700
+... procrustes: rmse 3.743805e-05 max resid 0.00011227
*** Solution reached
> ordihull(dune.ord, dune.env$Management)
@@ -4003,10 +4003,10 @@
> pl <- ordihull(mod, Management, scaling = 3, label = TRUE)
> ## ... and find centres and areas of the hulls
> summary(pl)
- BF HF NM SF
-CCA1 -0.2917476 -0.3682611 1.3505642 -0.2762936
-CCA2 0.8632208 0.0941992 0.2681515 -0.8139398
-Area 0.1951715 0.5994336 1.7398193 1.0144372
+ BF HF NM SF
+CCA1 -0.2917476 -0.36826105 1.3505642 -0.2762936
+CCA2 0.8632208 0.09419919 0.2681515 -0.8139398
+Area 0.1951715 0.59943363 1.7398193 1.0144372
> ## use ordispider to label and mark the hull
> plot(mod, type = "n")
> pl <- ordihull(mod, Management, scaling = 3)
@@ -4661,14 +4661,14 @@
converged
> with(varechem, ordisurf(vare.mds, Baresoil, bubble = 5))
Loading required package: mgcv
-This is mgcv 1.7-2. For overview type 'help("mgcv-package")'.
+This is mgcv 1.7-5. For overview type 'help("mgcv-package")'.
Family: gaussian
Link function: identity
Formula:
y ~ s(x1, x2, k = knots)
-<environment: 0x10234bed0>
+<environment: 0x467ea80>
Estimated degrees of freedom:
6.2955 total = 7.295494
@@ -4684,7 +4684,7 @@
Formula:
y ~ s(x1, x2, k = knots)
-<environment: 0x10538e238>
+<environment: 0x66d7a58>
Estimated degrees of freedom:
4.9207 total = 5.920718
@@ -4833,14 +4833,14 @@
> ## Map of PCNMs in the sample plot
> ordisurf(mite.xy, scores(pcnm1, choi=1), bubble = 4, main = "PCNM 1")
Loading required package: mgcv
-This is mgcv 1.7-2. For overview type 'help("mgcv-package")'.
+This is mgcv 1.7-5. For overview type 'help("mgcv-package")'.
Family: gaussian
Link function: identity
Formula:
y ~ s(x1, x2, k = knots)
-<environment: 0x1064ab778>
+<environment: 0x47d8f80>
Estimated degrees of freedom:
8.9275 total = 9.927492
@@ -4853,10 +4853,10 @@
Formula:
y ~ s(x1, x2, k = knots)
-<environment: 0x1067618b0>
+<environment: 0x6d9e7f8>
Estimated degrees of freedom:
-7.753 total = 8.75294
+7.7529 total = 8.75294
GCV score: 0.002284958
> ordisurf(mite.xy, scores(pcnm1, choi=3), bubble = 4, main = "PCNM 3")
@@ -4866,7 +4866,7 @@
Formula:
y ~ s(x1, x2, k = knots)
-<environment: 0x106033698>
+<environment: 0x711dbb8>
Estimated degrees of freedom:
8.8962 total = 9.89616
@@ -4957,7 +4957,7 @@
> ## time series within strata, with mirroring
> permCheck(pyrifos, control = permControl(strata = ditch,
+ type = "series", mirror = TRUE))
-[1] 1.285500e+16
+[1] 1.2855e+16
>
> ## time series within strata, no mirroring, same permutation within strata
> permCheck(pyrifos, control = permControl(strata = ditch,
@@ -5697,9 +5697,9 @@
Partitioning of mean squared contingency coefficient:
Inertia Proportion
-Total 2.115 1.0000
-Constrained 1.139 0.5385
-Unconstrained 0.976 0.4615
+Total 2.1153 1.0000
+Constrained 1.1392 0.5385
+Unconstrained 0.9761 0.4615
Eigenvalues, and their contribution to the mean squared contingency coefficient
@@ -6013,8 +6013,8 @@
Chealb 1.5737337 0.7842538 -0.5503660 -0.35108333
> # New sites
> predict(mod, type="lc", new=data.frame(A1 = 3, Management="NM", Moisture="2"), scal=2)
- CCA1 CCA2 CCA3 CCA4
-1 -2.388290 1.230652 0.2363485 0.3338258
+ CCA1 CCA2 CCA3 CCA4
+1 -2.38829 1.230652 0.2363485 0.3338258
> # Calibration and residual plot
> mod <- cca(dune ~ A1 + Moisture, dune.env)
> pred <- calibrate(mod)
@@ -6540,10 +6540,10 @@
Sites 37.000000 38.000000 39.000000 40.000000 41.000000 42.000000
Richness 218.160000 218.770000 219.340000 219.970000 220.600000 221.210000
sd 2.364382 2.210421 2.041093 2.071719 1.964328 1.945183
-
-Sites 43.000000 44.000000 45.000000 46.000000 47.000000 48.0000000
-Richness 221.850000 222.360000 222.890000 223.320000 223.710000 224.1700000
-sd 1.771691 1.586050 1.490000 1.476277 1.208514 0.9749903
+
+Sites 43.000000 44.00000 45.00 46.000000 47.000000 48.0000000
+Richness 221.850000 222.36000 222.89 223.320000 223.710000 224.1700000
+sd 1.771691 1.58605 1.49 1.476277 1.208514 0.9749903
Sites 49.0000000 50
Richness 224.6500000 225
@@ -6612,27 +6612,27 @@
Mean :216.4 Mean :217 Mean :217.6 Mean :218.2 Mean :218.8
3rd Qu.:218.0 3rd Qu.:219 3rd Qu.:219.0 3rd Qu.:220.0 3rd Qu.:220.0
Max. :222.0 Max. :222 Max. :223.0 Max. :223.0 Max. :224.0
- 39 sites 40 sites 41 sites 42 sites
- Min. :214.0 Min. :214.0 Min. :216.0 Min. :216.0
- 1st Qu.:218.0 1st Qu.:219.0 1st Qu.:219.0 1st Qu.:220.0
- Median :220.0 Median :220.0 Median :221.0 Median :221.0
- Mean :219.3 Mean :220.0 Mean :220.6 Mean :221.2
- 3rd Qu.:221.0 3rd Qu.:222.0 3rd Qu.:222.0 3rd Qu.:223.0
- Max. :224.0 Max. :224.0 Max. :224.0 Max. :225.0
- 43 sites 44 sites 45 sites 46 sites
- Min. :217.0 Min. :217.0 Min. :219.0 Min. :219.0
- 1st Qu.:221.0 1st Qu.:221.8 1st Qu.:222.0 1st Qu.:223.0
- Median :222.0 Median :223.0 Median :223.0 Median :224.0
- Mean :221.8 Mean :222.4 Mean :222.9 Mean :223.3
- 3rd Qu.:223.0 3rd Qu.:223.0 3rd Qu.:224.0 3rd Qu.:224.0
+ 39 sites 40 sites 41 sites 42 sites 43 sites
+ Min. :214.0 Min. :214 Min. :216.0 Min. :216.0 Min. :217.0
+ 1st Qu.:218.0 1st Qu.:219 1st Qu.:219.0 1st Qu.:220.0 1st Qu.:221.0
+ Median :220.0 Median :220 Median :221.0 Median :221.0 Median :222.0
+ Mean :219.3 Mean :220 Mean :220.6 Mean :221.2 Mean :221.8
+ 3rd Qu.:221.0 3rd Qu.:222 3rd Qu.:222.0 3rd Qu.:223.0 3rd Qu.:223.0
+ Max. :224.0 Max. :224 Max. :224.0 Max. :225.0 Max. :225.0
+ 44 sites 45 sites 46 sites 47 sites
+ Min. :217.0 Min. :219.0 Min. :219.0 Min. :220.0
+ 1st Qu.:221.8 1st Qu.:222.0 1st Qu.:223.0 1st Qu.:223.0
+ Median :223.0 Median :223.0 Median :224.0 Median :224.0
+ Mean :222.4 Mean :222.9 Mean :223.3 Mean :223.7
+ 3rd Qu.:223.0 3rd Qu.:224.0 3rd Qu.:224.0 3rd Qu.:225.0
Max. :225.0 Max. :225.0 Max. :225.0 Max. :225.0
- 47 sites 48 sites 49 sites 50 sites
- Min. :220.0 Min. :221.0 Min. :222.0 Min. :225
- 1st Qu.:223.0 1st Qu.:224.0 1st Qu.:224.0 1st Qu.:225
- Median :224.0 Median :224.0 Median :225.0 Median :225
- Mean :223.7 Mean :224.2 Mean :224.7 Mean :225
- 3rd Qu.:225.0 3rd Qu.:225.0 3rd Qu.:225.0 3rd Qu.:225
- Max. :225.0 Max. :225.0 Max. :225.0 Max. :225
+ 48 sites 49 sites 50 sites
+ Min. :221.0 Min. :222.0 Min. :225
+ 1st Qu.:224.0 1st Qu.:224.0 1st Qu.:225
+ Median :224.0 Median :225.0 Median :225
+ Mean :224.2 Mean :224.7 Mean :225
+ 3rd Qu.:225.0 3rd Qu.:225.0 3rd Qu.:225
+ Max. :225.0 Max. :225.0 Max. :225
> plot(sp1, ci.type="poly", col="blue", lwd=2, ci.lty=0, ci.col="lightblue")
> boxplot(sp2, col="yellow", add=TRUE, pch="+")
> ## Fit Arrhenius model
@@ -6674,7 +6674,7 @@
some notches went outside hinges ('box'): maybe set notch=FALSE
> boxplot(specnumber(dune)/specpool2vect(pool) ~ Management, col="hotpink",
+ border="cyan3", notch=TRUE)
-Warning in bxp(list(stats = c(0.465517241379310, 0.491379310344828, 0.517241379310345, :
+Warning in bxp(list(stats = c(0.46551724137931, 0.491379310344828, 0.517241379310345, :
some notches went outside hinges ('box'): maybe set notch=FALSE
> par(op)
> data(BCI)
@@ -6857,6 +6857,94 @@
>
>
> cleanEx()
+> nameEx("tolerance")
+> ### * tolerance
+>
+> flush(stderr()); flush(stdout())
+>
+> ### Name: tolerance
+> ### Title: Species tolerances and sample heterogeneities
+> ### Aliases: tolerance tolerance.cca print.tolerance.cca
+>
+> ### ** Examples
+>
+> data(dune)
+> data(dune.env)
+> mod <- cca(dune ~ ., data = dune.env)
+>
+> ## defaults to species tolerances
+> tolerance.cca(mod)
+
+ Species Tolerances
+
+Scaling: 2
+
+ CCA1 CCA2
+Belper 1.1917539 9.067794e-01
+Empnig 0.1354109 4.260585e-09
+Junbuf 1.2030350 5.294370e-01
+Junart 1.4857922 9.536362e-01
+Airpra 1.1366065 4.080607e-01
+Elepal 1.7546413 8.292822e-01
+Rumace 1.1961493 7.625654e-01
+Viclat 1.4806588 4.896853e-01
+Brarut 1.0600419 1.051819e+00
+Ranfla 1.6515397 1.059420e+00
+Cirarv 0.5464178 1.010898e-09
+Hyprad 1.0228811 5.791210e-01
+Leoaut 1.1005249 1.036536e+00
+Potpal 1.9934851 5.677653e-01
+Poapra 0.9755201 9.166587e-01
+Calcus 1.4830852 8.464129e-01
+Tripra 1.6458942 2.811272e-01
+Trirep 0.8832545 8.738483e-01
+Antodo 1.6055439 7.575379e-01
+Salrep 0.7118892 8.654457e-02
+Achmil 1.5948052 8.449914e-01
+Poatri 0.7367577 7.099165e-01
+Chealb 1.9479718 6.661338e-16
+Elyrep 0.5160932 5.135604e-01
+Sagpro 1.3031750 1.019154e+00
+Plalan 1.7013794 6.393173e-01
+Agrsto 1.5333793 8.718601e-01
+Lolper 0.9372994 7.874610e-01
+Alogen 1.3282695 3.464157e-01
+Brohor 0.9942186 5.515502e-01
+
+>
+> ## sample heterogeneities for CCA axes 1:6
+> tolerance.cca(mod, which = "sites", choices = 1:6)
+
+ Sample Heterogeneities
+
+Scaling: 2
+
+ CCA1 CCA2 CCA3 CCA4 CCA5 CCA6
+2 0.3704376 0.4136311 0.2577614 0.4568628 0.4195810 0.3008441
+13 1.5316319 0.8859365 1.3123835 1.1171402 1.1864910 1.3897352
[TRUNCATED]
To get the complete diff run:
svnlook diff /svnroot/vegan -r 1558
More information about the Vegan-commits
mailing list