dyn.pca: Dynamic PCA

In fnets: Factor-Adjusted Network Estimation and Forecasting for High-Dimensional Time Series

Dynamic PCA

Description

Performs principal components analysis in frequency domain for identifying common and idiosyncratic components.

Usage

dyn.pca(
  xx,
  q = NULL,
  q.method = c("ic", "er"),
  ic.op = 5,
  kern.bw = NULL,
  mm = NULL
)

Arguments

xx	centred input time series matrix, with each row representing a variable
q	number of factors. If q = NULL, the factor number is estimated by an information criterion-based approach of Hallin and Liška (2007)
q.method	A string specifying the factor number selection method; possible values are: "ic" information criteria-based methods of Alessi, Barigozzi & Capasso (2010) when fm.restricted = TRUE or Hallin and Liška (2007) when fm.restricted = FALSE "er" eigenvalue ratio of Ahn and Horenstein (2013)
ic.op	choice of the information criterion penalty. Currently the three options from Hallin and Liška (2007) (ic.op = 1, 2 or 3) and their variations with logarithm taken on the cost (ic.op = 4, 5 or 6) are implemented, with ic.op = 5 recommended as a default choice based on numerical experiments
kern.bw	a positive integer specifying the kernel bandwidth for dynamic PCA; by default, it is set to floor(4 *(dim(x)[2]/log(dim(x)[2]))^(1/3)))
mm	bandwidth

Value

a list containing

q	number of factors
q.method.out	if q = NULL, the output from the chosen q.method, either a vector of eigenvalue ratios or hl.factor.number
spec	a list containing the estimates of the spectral density matrices for x, common and idiosyncratic components
acv	a list containing estimates of the autocovariance matrices for x, common and idiosyncratic components
kern.bw	input parameter

fnets documentation built on May 29, 2024, 8:42 a.m.