RDA

Source: R/b_analyse.R

RDA

myRDA(
  otutab,
  env,
  norm = TRUE,
  scale = FALSE,
  choose_var = FALSE,
  direction = "forward",
  nperm = 499,
  verbose = TRUE,
  method = "rda",
  dist = "bray"
)

myCCA(
  otutab,
  env,
  norm = TRUE,
  scale = FALSE,
  choose_var = FALSE,
  nperm = 499,
  verbose = TRUE
)

myCAP(
  otutab,
  env,
  norm = TRUE,
  scale = FALSE,
  choose_var = FALSE,
  nperm = 499,
  verbose = TRUE,
  dist = "bray"
)

Arguments

otutab

an otutab data.frame, samples are columns, taxs are rows.

env

environmental factors

norm

should normalize? (default:TRUE)

scale

should scale species? (default:FALSE)

choose_var

should choose variables? use forward step

direction

The direction of the stepwise selection, "both", "forward" or "backward", default is "forward"

nperm

number of permutation

verbose

verbose

method

"rda", "cca", "cap", "dbrda"

dist

The name of the dissimilarity (or distance) index for "cap" or "dbrda", for vegdist

Value

rda/cca

See also

vegdist;unifrac

Examples

data(otutab, package = "pcutils")
env <- metadata[, 6:10]
# RDA
myRDA(otutab, env) -> phy.rda
#> ==================================Check models================================== 
#> DCA analysis, select the sorting analysis model according to the first value of the Axis lengths row.
#> - If it is more than 4.0 - CCA (based on unimodal model, canonical correspondence analysis);
#> - If it is between 3.0-4.0 - both RDA/CCA;
#> - If it is less than 3.0 - RDA (based on linear model, redundancy analysis)
#> 
#> Call:
#> vegan::decorana(veg = dat.h) 
#> 
#> Detrended correspondence analysis with 26 segments.
#> Rescaling of axes with 4 iterations.
#> Total inertia (scaled Chi-square): 0.3192 
#> 
#>                         DCA1    DCA2    DCA3     DCA4
#> Eigenvalues          0.03142 0.02276 0.01927 0.017818
#> Additive Eigenvalues 0.03142 0.02276 0.01927 0.017881
#> Decorana values      0.03169 0.02142 0.01511 0.009314
#> Axis lengths         0.73929 0.72605 0.52357 0.666913
#> 
#> =================================Initial Model================================== 
#> Initial cca, vif>20 indicates serious collinearity:
#>     env4     env5     env6      lat     long 
#> 2.574997 2.674671 1.252002 1.381839 1.211392 
#> Initial Model R-square: 0.04828743 
#> ===================================Statistics=================================== 
#> 0.3282029 constrained indicates the degree to which environmental factors explain differences in community structure
#> 0.6717971 unconstrained means that the environmental factors cannot explain the part of the community structure
RDA_plot(phy.rda, "Group", metadata)