Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/241155 
Year of Publication: 
2021
Series/Report no.: 
Staff Report No. 962
Publisher: 
Federal Reserve Bank of New York, New York, NY
Abstract: 
We analyze a model for N different measurements of a persistent latent time series when measurement errors are mean-reverting, which implies a common trend among measurements. We study the consequences of overdifferencing, finding potentially large biases in maximum likelihood estimators of the dynamics parameters and reductions in the precision of smoothed estimates of the latent variable, especially for multiperiod objects such as quinquennial growth rates. We also develop an R2 measure of common trend observability that determines the severity of misspecification. Finally, we apply our framework to U.S. quarterly data on GDP and GDI, obtaining an improved aggregate output measure.
Subjects: 
cointegration
GDP
GDI
overdifferencing
signal extraction
JEL: 
C32
E01
Document Type: 
Working Paper

Files in This Item:
File
Size
1.24 MB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.