kpe: determine factor number - projected

In OLCPM: Online Change Point Detection for Matrix-Valued Time Series

determine factor number - projected

Description

This function determined the numbers of row and column factors for matrix variate data under a two-way factor model, using a projected method.

Usage

kpe(Y, kmax = 4, c = 0)

Arguments

Y	data, a T\times p1\times p2 array.
kmax	a positive integer smaller than p2, indicating the upper bound for the factor numbers, and the dimension of projection matrix.
c	a non-negative but small number, to ensure the denominator of the eigenvalue ratio statistics is not 0.

Value

a 2-dimensional vector containing the estimated number of row and column factors, respectively.

References

Yu L, He Y, Kong X, & Zhang X (2022). Projected estimation for large-dimensional matrix factor models. Journal of Econometrics, 229(1),201-217.

Examples

k1=3
k2=3
Sample_T=100
p1=40
p2=20
kmax=8

Y=gen.data(Sample_T,p1,p2,k1,k2,tau=0.5,change=0)
kpe(Y,kmax)

OLCPM documentation built on June 22, 2024, 9:26 a.m.