fdapace (version 0.6.0)

kCFC: Functional clustering and identifying substructures of longitudinal data using kCFC.

Description

Functional clustering and identifying substructures of longitudinal data using kCFC.

Usage

kCFC(
  y,
  t,
  k = 3,
  kSeed = 123,
  maxIter = 125,
  optnsSW = list(methodMuCovEst = "smooth", FVEthreshold = 0.9, methodBwCov = "GCV",
    methodBwMu = "GCV"),
  optnsCS = list(methodMuCovEst = "smooth", FVEthreshold = 0.7, methodBwCov = "GCV",
    methodBwMu = "GCV")
)

Value

A list containing the following fields:

cluster

A vector of levels 1:k, indicating the cluster to which each curve is allocated.

fpcaList

A list with the fpcaObj for each separate cluster.

iterToConv

A number indicating how many iterations where required until convergence.

Arguments

y

A list of n vectors containing the observed values for each individual. Missing values specified by NAs are supported for dense case (dataType='dense').

t

A list of n vectors containing the observation time points for each individual corresponding to y.

k

A scalar defining the number of clusters to define; default 3. Values that define very small clusters (eg.cluster size <=3) will potentially err.

kSeed

A scalar valid seed number to ensure replication; default: 123

maxIter

A scalar defining the maximum number of iterations allowed; default 20, common for both the simple kmeans initially and the subsequent k-centres

optnsSW

A list of options control parameters specified by list(name=value) to be used for sample-wide FPCA; by default: "list( methodMuCovEst ='smooth', FVEthreshold= 0.90, methodBwCov = 'GCV', methodBwMu = 'GCV' )". See `Details in ?FPCA'.

optnsCS

A list of options control parameters specified by list(name=value) to be used for cluster-specific FPCA; by default: "list( methodMuCovEst ='smooth', FVEthreshold= 0.70, methodBwCov = 'GCV', methodBwMu = 'GCV' )". See `Details in ?FPCA'.

References

Jeng-Min Chiou, Pai-Ling Li, "Functional clustering and identifying substructures of longitudinal data." Journal of the Royal Statistical Society 69 (2007): 679-699

Examples

# \donttest{
data(medfly25) 
Flies <- MakeFPCAInputs(medfly25$ID, medfly25$Days, medfly25$nEggs)
kcfcObj <- kCFC(Flies$Ly[1:150], Flies$Lt[1:150], # using only 150 for speed consideration 
                 optnsSW = list(methodMuCovEst = 'smooth', userBwCov = 2, FVEthreshold = 0.90),
                 optnsCS = list(methodMuCovEst = 'smooth', userBwCov = 2, FVEthreshold = 0.70))
# }