pca_dfm

<p>Implements dimensionality reduction techniques for panel data including
PCA with bootstrap significance testing and Dynamic Factor Models (DFM)
for extracting common latent factors.</p>

Provides a comprehensive toolkit for extracting latent signals from
panel data through multivariate time series analysis. Implements spectral
decomposition methods including wavelet multiresolution analysis via maximal
overlap discrete wavelet transform, Percival and Walden (2000)
<doi:10.1017/CBO9780511841040>, empirical mode decomposition for
non-stationary signals, Huang et al. (1998) <doi:10.1098/rspa.1998.0193>,
and Bayesian trend extraction via the Grant-Chan embedded Hodrick-Prescott
filter, Grant and Chan (2017) <doi:10.1016/j.jedc.2016.12.007>. Features
Bayesian variable selection through regularized Horseshoe priors, Piironen
and Vehtari (2017) <doi:10.1214/17-EJS1337SI>, for identifying structurally
relevant predictors from high-dimensional candidate sets. Includes dynamic
factor model estimation, principal component analysis with bootstrap
significance testing, and automated technical interpretation of signal
morphology and variance topology.

José Mauricio Gómez Julián

SignalY

pca_dfm: Principal Component Analysis and Dynamic Factor Models

Description

Arguments