betaper (version 1.1-2)

rda_pertables: Function to assess the efects of taxonomic uncertainty on [Partial] Redundance Analysis

Description

This function asses the effects of taxonomic uncertainty on two widely used parameters of a [Partial] Redundance Analysis, i.e. the 'percentage explained variance' (sometimes referred to as R-squared) and the 'pseudo-F' .

Usage

rda_pertables(fml, data, scale=FALSE,...)
# S3 method for rda_pertables
plot (x, pch = 18, ...)

Arguments

fml

Model formula, where the left hand side gives a pertables object (i.e. a list of simulated community data matrices obtained with pertables, right hand side gives the constraining variables, and conditioning variables can be given within a special function Condition.

data

Data frame containing the variables on the right hand side of the model formula.

scale

Scale species to unit variance (like correlations).

x

rda_pertables object to plot.

pch

Plotting 'character', i.e., symbol to use in the RDA plot. See points for examples of use of this graphical argument.

…

Additional graphical parameters passed to plot.

Value

rda_pertables returns an object of class'rda_pertables', basically a list with the following components:

raw

An object of class class'rda'. The results of applying rda to the original biological data table without the unidentified species.

simulation

A list with the results of the simulation: 'results', i.e. a data.frame with all the simulated R-squared and pseudo-F values; 'rda.quant', i.e. a data.frame with the summary of 'results' by quantiles; 'sites' i.e. a list with the scores of the sites of all the simulated data tables and 'biplot', i.e. a list with the scores of the environmental data in all the analyses

The objects of class 'rda_pertables' have print and plot S3 methods for a simple access to results. See the examples.

Details

This function is a wrapper to submit a pertables object to rda function of the vegan package. See the documentation of cca for details about formula and Condition use.

References

Cayuela, L., De la Cruz, M. and Ruokolainen, K. (2011). A method to incorporate the effect of taxonomic uncertainty on multivariate analyses of ecological data. Ecography, 34: 94-102. http://dx.doi.org/10.1111/j.1600-0587.2009.05899.x.

See Also

pertables, cca

Examples

# NOT RUN {
 


data(Amazonia)
data(soils)

# Define a new index that includes the terms used in the \code{Amazonia} dataset to define
# undetermined taxa at different taxonomic levels

index.Amazon <- c(paste("sp.", rep(1:20), sep=""), "Indet.", "indet.")


#Generate a pertables object (i.e. a list of biological data tables simulated from taxonomic
# uncertainty)
 
# }
# NOT RUN {
Amazonia100 <- pertables(Amazonia, index=index.Amazon, nsim=100)

# Assess the effects of taxonomic uncertainty on a RDA analysis of biological data explained
# by all the environmental variables of the soil data:

Amazonia.rda <- rda_pertables(Amazonia100 ~., data=soils)

Amazonia.rda

plot(Amazonia.rda)
 
# }
# NOT RUN {
# Fast example for Rcheck

Amazonia4.p2 <- pertables.p2(Amazonia[1:50,], index=index.Amazon, nsim=4, ncl=2, iseed=4)
set.seed(2)
Amazonia.rda <- rda_pertables(Amazonia4.p2 ~., data=soils)

Amazonia.rda

plot(Amazonia.rda)
 

# }