Learn R Programming

sparseDFM (version 1.0)

Estimate Dynamic Factor Models with Sparse Loadings

Description

Implementation of various estimation methods for dynamic factor models (DFMs) including principal components analysis (PCA) Stock and Watson (2002) , 2Stage Giannone et al. (2008) , expectation-maximisation (EM) Banbura and Modugno (2014) , and the novel EM-sparse approach for sparse DFMs Mosley et al. (2023) . Options to use classic multivariate Kalman filter and smoother (KFS) equations from Shumway and Stoffer (1982) or fast univariate KFS equations from Koopman and Durbin (2000) , and options for independent and identically distributed (IID) white noise or auto-regressive (AR(1)) idiosyncratic errors. Algorithms coded in 'C++' and linked to R via 'RcppArmadillo'.

Copy Link

Version

Install

install.packages('sparseDFM')

Monthly Downloads

243

Version

1.0

License

GPL (>= 3)

Maintainer

Alex Gibberd

Last Published

March 23rd, 2023

Functions in sparseDFM (1.0)

tuneFactors

Tune for the number of factors to use
summary.sparseDFM

sparseDFM Summary Outputs
transformData

Transform data to make it stationary
sparseDFM

Estimate a Sparse Dynamic Factor Model
residuals.sparseDFM

sparseDFM Residuals and Fitted Values
predict.sparseDFM

Forecasting factor estimates and data series.
kalmanUnivariate

Univariate filtering (sequential processing) for fast KFS
kalmanMultivariate

Classic Multivariate KFS Equations
plot.sparseDFM

sparseDFM Plot Outputs
fillNA

Interpolation of missing data
missing_data_plot

Plot the missing data in a data matrix/frame
exports

UK Trade in Goods (Exports) Dataset
logspace

logspace
raggedEdge

Generate a ragged edge structure for a data matrix
inflation

UK Inflation Dataset