BS_local_factor: Get a bootstrap confidence interval for the local factors

In GCCfactor: GCC Estimation of the Multilevel Factor Model

Get a bootstrap confidence interval for the local factors

Description

This function employs a bootstrap procedure to obtain confidence intervals for the local factors in block i at time t. See Lin and Shin (2023) for details.

Usage

BS_local_factor(object, i, t, BB = 599, alpha = 0.05)

Arguments

object	An S3 object of class 'multi_result' created by multilevel().
i	An integer indicating the i-th block.
t	An integer specifying the time point at which the CI is constructed.
BB	An integer indicating the number of bootstrap repetition. 599 by default.
alpha	The significance level, a single numeric between 0 and 1. 0.05 by default.

Value

A matrix containing the upper and lower band.

References

Lin, R. and Shin, Y., 2022. Generalised Canonical Correlation Estimation of the Multilevel Factor Model. Available at SSRN 4295429.

Examples

panel <- UKhouse # load the data
est_multi <- multilevel(panel, ic = "BIC3", standarise = TRUE, r_max = 5,
                           depvar_header = "dlPrice", i_header = "Region",
                           j_header = "LPA_Type", t_header = "Date")
bs_local_factor_11 <- BS_local_factor(est_multi, i = 1, t = 1)

GCCfactor documentation built on Nov. 2, 2023, 5:59 p.m.