Metadata only
Date
2013Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
Although many official statistics are jointly produced by statistica agencies, data revisions in individual time series are typically studied in isolation ignoring information in other related series. This paper extends the Jacobs and van Norden (2011) modeling framework to multivariate data revisions. We consider systems of variables, where true values and news and noise can be correlated, and which may be linked by one or more identities. We show how to model such systems with standard linear state space models. We motivate and illustrate the multivariate modeling framework with Swiss current account data using Bayesian econometric methods for estimation and inference and thereby produce estimates of the underlying true values together with their respective error bands. Show more
Publication status
publishedBook title
9th Annual CIRANO-CIREQ Workshop on Data Revision in Macroeconomic Forecasting and Policy, ProgramPublisher
CIRANOEvent
Organisational unit
02525 - KOF Konjunkturforschungsstelle / KOF Swiss Economic Institute
03716 - Sturm, Jan-Egbert / Sturm, Jan-Egbert
Notes
Conference lecture on October 12, 2013.More
Show all metadata
ETH Bibliography
yes
Altmetrics