albatross (version 0.1-1)

plot.feemjackknife: Plot jack-knifing results

Description

Plot the results of PARAFAC jack-knifing of a dataset.

Usage

# S3 method for feemjackknife
plot(
    x, kind = c('estimations', 'RIP', 'IMP'), …
  )

Arguments

x

An object returned by feemjackknife.

kind

"estimations"

Plot the loadings from every leave-one-out model.

"RIP"

Produce a Resample Influence Plot, i.e. plot mean squared difference between loadings in overall and leave-one-out models against mean squared residuals in leave-one-out models.

"IMP"

Produce an Identity Match Plot, i.e. plot scores in leave-one-out models against scores in overall model.

…

When kind is "RIP" or "IMP", pass a q argument to specify the quantile of residual values (for RIP) or absolute score differences (IMP) above which sample names (or numbers) should be plotted.

Passed as-is to xyplot.

Value

A lattice plot object. Its print or plot method will draw the plot on an appropriate plotting device.

Details

The function provides sane defaults for xyplot parameters xlab, ylab, scales, as.table, but they can be overridden.

References

J. Riu, R. Bro, Jack-knife technique for outlier detection and estimation of standard errors in PARAFAC models, Chemometrics and Intelligent Laboratory Systems. 65 (2003) 35-49. 10.1016/S0169-7439(02)00090-4

See Also

feemjackknife

Examples

# NOT RUN {
  data(feems)
  cube <- feemscale(
    feemscatter(feemcube(feems, FALSE), rep(24, 4)), na.rm = TRUE
  )
  plot( # jack-knifing takes a long time
    jk <- feemjackknife(cube, nfac = 2, const = rep('nonneg', 3))
  )
  plot(jk, 'IMP')
  plot(jk, 'RIP')
# }