plotVariofaces.data.frame {asremlPlus}

Plots empirical variogram faces, including envelopes, from supplied residuals as described by Stefanova, Smith & Cullis (2009).

Description

Produces a plot for each face of an empirical 2D variogram based on supplied residuals from both an observed data set and simulated data sets. Those from simulated data sets are used to produce confidence envelopes If the data consists of sections, such as separate experiments, the two variogram faces are produced for each section. This function is less efficient in storage terms than variofaces.asreml, because here the residuals from all simulated data sets must be saved, in addition to the values for the variogram faces; in variofaces.asreml, the residuals for each simulated data set are discarded after the variogram has been calculated. On the other hand, the present function is more flexible, because there is no restriction on how the residuals are obtained.

Usage

## S3 method for class 'data.frame'
plotVariofaces(data, residuals, restype="Residuals", ...)

Arguments

data

A data.frame with either 3 or 4 columns. Only if there are 4 columns, the first should be a factor indexing sections for which separate variogram plots are to be produced. In either case, the other 3 columns should be, in order, (i) a factor indexing the x-direction, (ii) a factor indexing the y-direction, and (iii) the residuals for the observed response.

residuals

A data.frame, with either 2 or 3 initial columns followed by columns, each of which are the residuals from a simulated data set.

restype

A character describing the type of residuals that have been supplied. It will be used in the plot titles.

...

Other arguments that are passed down to the function asreml.variogram.

Details

For each set of residuals, asreml.variogram is used to obtain the empirical variogram, from which the values for its faces are obtained. Plots are produced for each face and include the observed residuals and the 2.5%, 50% & 97.5% quantiles.

Value

A list with the following components:

1. face1: a data.frame containing the variogram values on which the plot for the first dimension is based.

2. face2: a data.frame containing the variogram values on which the plot for the second dimension is based.

Author(s)

Chris Brien

References

Stefanova, K. T., Smith, A. B. & Cullis, B. R. (2009) Enhanced diagnostics for the spatial analysis of field trials. Journal of Agricultural, Biological, and Environmental Statistics, 14, 392–410.

See Also

asremlPlus-package, asreml, asreml.variogram, variofaces.asreml, simulate.asreml.

Examples

## Not run: 
data(Wheat.dat)
current.asr <- asreml(yield ~ Rep + WithinColPairs + Variety, 
                      random = ~ Row + Column + units,
                      residual = ~ ar1(Row):ar1(Column), 
                      data=Wheat.dat)
current.asrt <- as.asrtests(current.asr, NULL, NULL)
current.asrt <- rmboundary.asrtests(current.asrt)
# Form variance matrix based on estimated variance parameters
s2 <- current.asr$sigma2
gamma.Row <- current.asr$gammas[1]
gamma.unit <- current.asr$gammas[2]
rho.r <- current.asr$gammas[4]
rho.c <- current.asr$gammas[5]
row.ar1 <- mat.ar1(order=10, rho=rho.r)
col.ar1 <- mat.ar1(order=15, rho=rho.c)
V <- gamma.Row * fac.sumop(Wheat.dat$Row) + 
  gamma.unit * diag(1, nrow=150, ncol=150) + 
  mat.dirprod(col.ar1, row.ar1)
V <- s2*V

#Produce variogram faces plot (Stefanaova et al, 2009)
resid <- simulate(current.asr, V=V, which="residuals")
resid$residuals <- cbind(resid$observed[c("Row","Column")],
                         resid$residuals)
plotVariofaces(data=resid$observed[c("Row","Column","residuals")],
               residuals=resid$residuals, 
               restype="Standardized conditional residuals")

## End(Not run)