Readme file
SERIES C
 Applied Statistics
Dynamic factor analysis with non-linear temporal aggregation constraints, by T. Proietti and F. Moauro
Appl. Statist., Volume
55 (2006), 281 - 300
DATA SETS AND COMPUTER PROGRAMS
The data for the estimation of the US index of coincident indicators are available in two separate .csv files
1. US_GDP_Quarterly.csv
GDP: Quarterly real gross domestic product in billions of chained 1996 dollars
Source: Department of Commerce, Bureau of Economic Analysis.
2. NBER_Monthly_Indicators.csv (see Section 6 of the paper for more details)
The file contains four monthly time series
IIP: Index of industrial production, base 1997 = 100.
EMP: Employment, number of employees on non-agricultural payrolls in thousands
SLS: Manufactured and trade sales in millions of chained 1996 dollars
INC: Personal income less transfer payments in billions of chained 1996 dollars
The file US_IndexCoincInd.ox contains a set of Ox functions (see Doornik, J.A. (2001). "Ox 3.0 - an Object-Oriented Matrix Programming Language", Timberlake Consultants Ltd, London) for filtering and smoothing, maximum likelihood inference and diagnostics for dynamic factor analysis with non-linear aggregation constraints, as outlined in the paper.
The euro area time series are collected in four separate csv files:
1. IndustrialProduction.csv - Index of industrial production, monthly
2. RetailSales.csv - Index of retail sales, monthly
3. Employment.csv - Civilian employment total, quarterly
4. GrossDomesticProduct.csv - Gross domestic product at constant 1995 prices, quarterly
The Ox program EuroArea_IndexCoincInd.ox estimates the dynamic factor analysis with
nonlinear aggregation constraints for the euro area.
Tommaso Proietti
Dipartimento di Studi Economico-Finanziari e Metodi Quantitativi
Università di Roma "Tor Vergata"
Via Columbia 2
00133 Rome
Italy
E-mail: tommaso.proietti@uniroma2.it
Datasets (.zip,
size - 25KB) |
