Learn R Programming

⚠️There's a newer version (0.1.10) of this package.Take me there.

midasml (version 0.0.6)

Estimation and Prediction Methods for High-Dimensional Mixed Frequency Time Series Data

Description

The 'midasml' estimation and prediction methods for high dimensional time series regression models under mixed data sampling data structures using structured-sparsity penalties and orthogonal polynomials. For more information on the 'midasml' approach see Babii, Ghysels, and Striaukas (2021, JBES forthcoming) . Functions that compute MIDAS data structures were inspired by MIDAS 'Matlab' toolbox (v2.3) written by Eric Ghysels.

Copy Link

Version

Install

install.packages('midasml')

Monthly Downloads

892

Version

0.0.6

License

GPL (>= 2)

Maintainer

Jonas Striaukas

Last Published

March 12th, 2021

Functions in midasml (0.0.6)

apply_transform

Time series matrix transformation

Compute difference in two dates.

Computes cross-validation folds.

Beta density polynomial weights

Transform date vector to numeric matrix

Asymmetric least squares loss for ARDL-MIDAS or DL-MIDAS regression

Identify data frequency

cpp_sgl_fitpath

Computes a path solution for \(\lambda\) and fixed \(\gamma\) values

Exponential Almon polynomial weights

Legendre polynomials shifted to [a,b]

ARDL-MIDAS regression

Computes fast ALS solution

midasml_forecast

MIDAS ML regression prediction function

GDP nowcasting using midasML approach example data

mixed_freq_data

MIDAS data structure

MIDAS regression prediction function

MIDAS weights plot function

Computes fast OLS solution

path_calc_panel

Computes a sequence of lambda parameters for the sg-LASSO panel regression

Computes fast DL-MIDAS profiling solution

Computes a single solution for \(\lambda_1\) and \(\lambda_2\) values

Computes fast rq solution

Gegenbauer polynomials shifted to [a,b]

mixed_freq_data_mhorizon

MIDAS data structure

mixed_freq_data_single

MIDAS data structure

predict.panel_sgl

Computes prediction for the sg-LASSO panel regression model

Updates the cross-validation error estimates

DL-MIDAS regression

End of the month date

Linear sg-LASSO regression

MIDAS regression estimation function

Mean squared error loss for ARDL-MIDAS or DL-MIDAS regression

US real GDP data with several high-frequency predictors

Compute mode of a vector

Beginning of the month date

get_start_midas

MIDAS regression function for initial values

Time series vector transformation

sg-LASSO regression

Panel sg-LASSO regression model

Computes optimal \(\lambda\) for cross-validation output.

Computes fast ARDL-MIDAS profiling solution

qtarget.sort_midasml

High-dimensional mixed frequency data sort function

Computes a sequence of lambda parameters for the mse sg-LASSO regression

midasml-package

Compute the number of lags

Restricted Beta density polynomial weights

predict.reg_sgl

Computes prediction for the sg-LASSO linear regression

Quantile regression loss for ARDL-MIDAS or DL-MIDAS regression