Quantcast

ordiR2step() does not add variables

classic Classic list List threaded Threaded
1 message Options
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

ordiR2step() does not add variables

Ralf Schäfer-2
Dear all,

we encountered a problem with vegan::ordiR2step() with the RIKZ data set of Analysing ecological data.
We have posted this on SO, but may be of interest to several people on this list.
http://stackoverflow.com/questions/41937957/veganordir2step-doesnt-find-best-fit-model

Reproducible example:
library(vegan)
# data
RIKZ <- read.table("http://www.uni-koblenz-landau.de/en/campus-landau/faculty7/environmental-sciences/landscape-ecology/Teaching/RIKZ_data/at_download/file", header = TRUE)

# data preparation
Species  <- RIKZ[ ,2:5]
ExplVar <- RIKZ[ , 9:15]

Species_fin  <- Species[ rowSums(Species) > 0, ]
ExplVar_fin  <- ExplVar[ rowSums(Species) > 0, ]

# rda
RIKZ_rda <- rda(Species_fin ~ . , data = ExplVar_fin, scale = TRUE)

# stepwise model building: ordiR2step()
step_both_R2 <- ordiR2step(rda(Species_fin ~ salinity, data = ExplVar_fin, scale = TRUE), scope = formula(RIKZ_rda), direction = "both", R2scope = TRUE, Pin = 0.05, steps
= 1000)

Basically, ordiR2step() stops without adding the variable exposure to the model.
However, if setting R2scope to FALSE:

step_both_R2 <- ordiR2step(rda(Species_fin ~ salinity, data = ExplVar_fin, scale = TRUE), scope = formula(RIKZ_rda), direction = "both", R2scope = FALSE, Pin = 0.05, steps
= 1000)

exposure is added, but the function fails with:
Error in terms.formula(tmp, simplify = TRUE): invalid model formula in ExtractVars

However, we compared a data set for which the function runs properly and couldn’t find a reason why it is failing for this one.

Any help appreciated
Ralf

_______________________________________________
R-sig-ecology mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
Loading...