abc_crit: ABC criterion for choosing the number of static factors

In juhokalle/rmfd4dfm: Estimation of DFMs using RMFD-E parametrization

ABC criterion for choosing the number of static factors

Description

The function estimates the number of static factors in the dynamic factor model. These information criteria are based on Alessi, Barigozzi and Capasso (2010). This function is a direct translation of the MATLAB code given in http://www.barigozzi.eu/Codes.html written by Matteo Barigozzi.

Usage

abc_crit(X, kmax, nbck = NULL, cmax = 3)

Arguments

X	T x N data matrix
kmax	maximum number of factors
nbck	number of sublocks to be used, defaults to floor(N/10)
cmax	maximum value for the penalty constant, default is 3

Value

rhat1	determines the number of shocks using a large window
rhat2	determines the number of shocks using a small window

See Also

Alessi, L., M. Barigozzi, and M. Capasso (2010). Improved penalization for determining the number of factors in approximate static factor models. Statistics and Probability Letters 80, 1806-1813.

Examples

(abc1 <- abc_crit(X = FRED_heavy$df, kmax = 25))
(abc2 <- abc_crit(X = FRED_light$df, kmax = 25))

juhokalle/rmfd4dfm documentation built on July 18, 2024, 10:19 p.m.