prequential.score: Calculate prequential scores

Description

IMPORTANT: This is the DNAmixturesLite package, which is intended as a service to enable users to try DNAmixtures without purchasing a commercial licence for Hugin. When at all possible, we strongly recommend the use of DNAmixtures rather than this lite-version. See https://dnamixtures.r-forge.r-project.org/ for details on both packages.

While the lite-version seeks to provide the full functionality of DNAmixtures, note that computations are much less efficient and that there are some differences in available functionality. Be aware that the present documentation is copied from DNAmixtures and thus may not accurately describe the implementation of this lite-version.

Usage

prequential.score(mixture, pars, markers = mixture$markers, by.allele = TRUE)
# S3 method for prequential.score
plot(x, normalise = FALSE, ylab = NULL, ylim = NULL, ...)

Value

A data.frame, which contains the output from predict as well as columns Y, EY, VY, corresponding to the log-score and its mean and variance. Finally the variable score is added, which is the normalised cumulative log-score.

Arguments

mixture: A DNAmixture model object.
pars: A mixpar model parameter.
markers: An ordering of the markers, possibly a subset of the markers only.
by.allele: Should conditioning be done allele-wise (TRUE) or EPG-wise (FALSE). Defaults to TRUE. For details, see predict.
x: A data.frame containing at least variables marker and score.
normalise: Should the prequential score be normalised? Defaults to FALSE.
ylab: Label for the y-axis.
ylim: Range for the y-axis.
...: Additional arguments to be passed on to plot.

Author

Therese Graversen

Examples

Run this code

data(MC15, MC18, USCaucasian)
mix <- DNAmixture(list(MC15, MC18), C = list(50,50), k = 3, K = c("K1", "K3"),
                  database = USCaucasian)
p <- mixpar(rho = list(30, 30), eta = list(30, 30), xi = list(0.08,0.08),
            phi = list(c(U1 = 0.1, K3 = 0.2, K1 = 0.7), c(U1 = 0.1, K3 = 0.2, K1 = 0.7)))
preq <- prequential.score(mix, pars = p)
plot(preq, col = preq$trace)
## Annotate using repeat numbers
text(preq$score, labels = preq$allele, pos = c(1,3), col = preq$trace, cex = 0.6)