1 \name{diversity.contrast.test}
2 \alias{diversity.contrast.test}
3 \title{Diversity Contrast Test}
5 This function performs the diversity contrast test comparing pairs of
9 diversity.contrast.test(x, method = "ratiolog",
10 alternative = "two.sided", nrep = 0, ...)
13 \item{x}{a matrix or a data frame with at least two columns: the first
14 one gives the number of species in clades with a trait supposed to
15 increase or decrease diversification rate, and the second one the
16 number of species in the sister-clades without the trait. Each row
17 represents a pair of sister-clades.}
18 \item{method}{a character string specifying the kind of test:
19 \code{"ratiolog"} (default), \code{"proportion"},
20 \code{"difference"}, \code{"logratio"}, or any unambiguous
21 abbreviation of these.}
22 \item{alternative}{a character string defining the alternative
23 hypothesis: \code{"two.sided"} (default), \code{"less"},
24 \code{"greater"}, or any unambiguous abbreviation of these.}
25 \item{nrep}{the number of replications of the randomization test; by
26 default, a Wilcoxon test is done.}
27 \item{\dots}{arguments passed to the function
28 \code{\link[stats]{wilcox.test}}.}
31 If \code{method = "ratiolog"}, the test described in Barraclough et
32 al. (1996) is performed. If \code{method = "proportion"}, the version
33 in Barraclough et al. (1995) is used. If \code{method = "difference"},
34 the signed difference is used (Sargent 2004). If \code{method = "logratio"},
35 then this is Wiegmann et al.'s (1993) version. These
36 four tests are essentially different versions of the same test (Vamosi
37 and Vamosi 2005, Vamosi 2007). See Paradis (2012) for a comparison of
38 their statistical performance with other tests.
40 If \code{nrep = 0}, a Wilcoxon test is done on the species diversity
41 contrasts with the null hypothesis is that they are distributed around
42 zero. If \code{nrep > 0}, a randomization procedure is done where the
43 signs of the diversity contrasts are randomly chosen. This is used to
44 create a distribution of the test statistic which is compared with the
45 observed value (the sum of the diversity contrasts).
48 a single numeric value with the \emph{P}-value.
51 Barraclough, T. G., Harvey, P. H. and Nee, S. (1995) Sexual
52 selection and taxonomic diversity in passerine birds.
53 \emph{Proceedings of the Royal Society of London. Series B. Biological
54 Sciences}, \bold{259}, 211--215.
56 Barraclough, T. G., Harvey, P. H., and Nee, S. (1996) Rate of
57 \emph{rbc}L gene sequence evolution and species diversification in
58 flowering plants (angiosperms). \emph{Proceedings of the Royal Society
59 of London. Series B. Biological Sciences}, \bold{263}, 589--591.
61 Paradis, E. (2012) Shift in diversification in sister-clade
62 comparisons: a more powerful test. \emph{Evolution}, \bold{66},
65 Sargent, R. D. (2004) Floral symmetry affects speciation rates in
66 angiosperms. \emph{Proceedings of the Royal Society of London. Series
67 B. Biological Sciences}, \bold{271}, 603--608.
69 Vamosi, S. M. (2007) Endless tests: guidelines for analysing non-nested
70 sister-group comparisons. An addendum. \emph{Evolutionary Ecology
71 Research}, \bold{9}, 717.
73 Vamosi, S. M. and Vamosi, J. C. (2005) Endless tests: guidelines for
74 analysing non-nested sister-group comparisons. \emph{Evolutionary
75 Ecology Research}, \bold{7}, 567--579.
77 Wiegmann, B., Mitter, C. and Farrell, B. 1993. Diversification of
78 carnivorous parasitic insects: extraordinary radiation or specialized
79 dead end? \emph{American Naturalist}, \bold{142}, 737--754.
81 \author{Emmanuel Paradis}
83 \code{\link{slowinskiguyer.test}}, \code{\link{mcconwaysims.test}}
84 \code{\link{richness.yule.test}}
87 ### data from Vamosi & Vamosi (2005):
88 fleshy <- c(1, 1, 1, 1, 1, 3, 3, 5, 9, 16, 33, 40, 50, 100, 216, 393, 850, 947,1700)
89 dry <- c(2, 64, 300, 89, 67, 4, 34, 10, 150, 35, 2, 60, 81, 1, 3, 1, 11, 1, 18)
90 x <- cbind(fleshy, dry)
91 diversity.contrast.test(x)
92 diversity.contrast.test(x, alt = "g")
93 diversity.contrast.test(x, alt = "g", nrep = 1e4)
94 slowinskiguyer.test(x)