BM14_Models: Euro Area Macroeconomic Data from Banbura and Modugno 2014

In dfms: Dynamic Factor Models

Euro Area Macroeconomic Data from Banbura and Modugno 2014

Description

A data extract from BM 2014 replication files. Some proprietary series (mostly PMI's) are excluded. The dataset BM14_Models provides information about all series and their inclusion in the 'small', 'medium' and 'large' sized dynamic factor models estimated by BM 2014. The actual data is contained in xts format in BM14_M for monthly data and BM14_Q for quarterly data.

Usage

BM14_Models
BM14_M
BM14_Q

Format

BM14_Models is a data frame with 101 obs. (series) and 8 columns:

series

BM14 series code (converted to snake case for R)

label

BM14 series label

code

original series code from data source

freq

series frequency

log_trans

logical indicating whether the series was transformed by the natural log before differencing. Note that all data are provided in untransformed levels, and all data was (log-)differenced by BM14 before estimation.

small

logical indicating series included in the 'small' model of BM14. Proprietary series are excluded.

medium

logical indicating series included in the 'medium' model of BM14. Proprietary series are excluded.

large

logical indicating series included in the 'large' model of BM14. This comprises all series, thus the variable is redundant but included for completeness. Proprietary series are excluded.

Source

Banbura, M., & Modugno, M. (2014). Maximum likelihood estimation of factor models on datasets with arbitrary pattern of missing data. Journal of Applied Econometrics, 29(1), 133-160.

Examples

library(magrittr)
library(xts)

# Constructing the database for the large model
BM14 = merge(BM14_M, BM14_Q)
BM14[, BM14_Models$log_trans] %<>% log()
BM14[, BM14_Models$freq == "M"] %<>% diff()
BM14[, BM14_Models$freq == "Q"] %<>% diff(3)

# Small Model Database
head(BM14[, BM14_Models$small])

# Medium-Sized Model Database
head(BM14[, BM14_Models$medium])

dfms documentation built on June 22, 2024, 10:31 a.m.