ClusTorus (version 0.2.2)

hyperparam.J: Selecting optimal number of mixture components based on various criteria

Description

hyperparam.J evaluates criterion for each icp.torus objects, and select the optimal number of mixture components based on the evaluated criterion.

Usage

hyperparam.J(icp.torus.objects, option = c("risk", "AIC", "BIC"))
# S3 method for hyperparam.J
plot(x, ...)

Arguments

icp.torus.objects

a list whose elements are icp.torus objects, generated by icp.torus.

option

a string one of "risk", "AIC", or "BIC", which determines the criterion for the model selection. "risk" is based on the negative log-likelihood, "AIC" for the Akaike Information Criterion, and "BIC" for the Bayesian Information Criterion.

x

hyperparam.J object

...

additional parameter for ggplot2::ggplot()

Value

returns a hyperparam.J object which contains a data.frame for the evaluated criterion corresponding to each number of components, the optimal number of components, and the corresponding icp.torus object.

References

Jung, S., Park, K., & Kim, B. (2021). Clustering on the torus by conformal prediction. The Annals of Applied Statistics, 15(4), 1583-1603.

Akaike, H. (1974). A new look at the statistical model identification. IEEE transactions on automatic control, 19(6), 716-723.

Schwarz, G. (1978). Estimating the dimension of a model. The annals of statistics, 461-464.

See Also

icp.torus, hyperparam.torus, hyperparam.alpha

Examples

# NOT RUN {
data <- toydata1[,1:2]
n <- nrow(data)
split.id <- rep(2,n)
split.id[ sample(n,floor(n/2)) ] <- 1

Jvec = 4:20
icp.torus.objects <- icp.torus(data, split.id = split.id, model = "kmeans", J = Jvec)

hyperparam.J(icp.torus.objects, option = "AIC")
# }