IDbyDistanceDistInputCCV: Spatial Provenancing Correct Cross-Validation calculation...

In ArdernHB/GeoOrigins: Spatial exploration of trait boundaries and provenance

Spatial Provenancing Correct Cross-Validation calculation from distance data

Description

This function takes pairwise distances among all reference specimens with known spatial origins and uses those distances to calculate the correllation value that would be required to correctly provenancing them in a test. This is achieved by a leave-one-out procedure. If a cross-validation procedure that removes more than one specimen from the reference dataset is desired then it is recommended that the validate function of the IDbyDistanceDistInput method be used with the validate argument in a loop.

Usage

IDbyDistanceDistInputCCV(
  LatLongs,
  DistDataMat,
  Verbose = TRUE,
  PrintProg = TRUE,
  ProvConfidence = 0.95,
  Method = c("Pearson", "Spearman")
)

Arguments

LatLongs	a matrix of n rows by 2 columns where n is the number of reference specimens in your dataset and the columns are Latitude and Longitude values in that order. These latitude-longitude coordinates should be of the locations of the reference specimens.
DistDataMat	is a square matrix of pairwise distances among all reference specimens
Verbose	logical whether or not a matrix of spatial correlation values is returned or not. Default is set to TRUE.
PrintProg	logical whether or not to print a progress bar. Default set to FALSE.
ProvConfidence	is a value between 0 and 1 indicating the confidence level that is desired for spatial provenancing.
Method	determines what kind of correlation coefficient should be used, either "Spearman" or "Pearson". Spearman's ranked correlation coefficient does not assume a linear relationship between geographic and trait distances, whereas Pearson's coefficient does.

Details

This method also makes use of the cor.test function from the stats package. When the PrintProg is set to TRUE, the progress function of the svMisc package is used. The map plotting of this function makes use of the functions of the maps package.

Value

If Verbose is set to FALSE then a list of a single object containing the correlation value at the required confidence interval is returned. If Verbose is set to TRUE then a list is returned with two objects: the first is the correlation value at the required confidence interval; the second a dataframe of coordinates and the spatial-trait correlation values at the true locations of each specimen.

Citations

Original S code by Richard A. Becker, Allan R. Wilks. R version by Ray Brownrigg. Enhancements by Thomas P Minka and Alex Deckmyn. (2017). maps: Draw Geographical Maps. R package version 3.2.0. https://CRAN.R-project.org/package=maps

Grosjean, Ph. (2016). svMisc: SciViews-R. UMONS, Mons, Belgium. http://www.sciviews.org/SciViews-R.

Author(s)

Ardern Hulme-Beaman

RatDistMat <- ProcDistanceTable(Rpraetor$LMs)

Range.Exp <- .5

Long.Range <- c(floor(min(Rpraetor$Lat.Long$Long)) -Range.Exp,ceiling(max(Rpraetor$Lat.Long$Long)+Range.Exp))

Lat.Range <- c(floor(min(Rpraetor$Lat.Long$Lat)) -Range.Exp,ceiling(max(Rpraetor$Lat.Long$Lat)+Range.Exp))

rThres <- IDbyDistanceDistInputCCV(LatLongs = Rpraetor$Lat.Long, DistDataMat = RatDistMat, Verbose = TRUE, ProvConfidence = .95, PrintProg = FALSE, Method = 'Spearman')

ArdernHB/GeoOrigins documentation built on Nov. 19, 2022, 10:21 a.m.