Publication Type

Journal Article

Version

submittedVersion

Publication Date

7-2003

Abstract

Popular monthly coincident indices of business cycles, e.g. the composite index and the Stock-Watson coincident index, have two shortcomings. First, they ignore information contained in quarterly indicators such as real GDP. Second, they lack economic interpretation; hence the heights of peaks and the depths of troughs depend on the choice of an index. This paper extends the Stock-Watson coincident index by applying maximum likelihood factor analysis to a mixed-frequency series of quarterly real GDP and monthly coincident business cycle indicators. The resulting index is related to latent monthly real GDP. [PUBLICATION ABSTRACT]

Keywords

Factor analysis, Time series, Missing observation, State-space model, Kalman filter, Stock-Watson index

Discipline

Econometrics | Finance

Research Areas

Econometrics

Publication

Journal of Applied Econometrics

Volume

18

Issue

4

First Page

427

Last Page

443

ISSN

0883-7252

Identifier

10.1002/jae.695

Publisher

Wiley

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1002/jae.695

Share

COinS