Data Revisions Are Not Well Behaved

By S. B. Aruoba. 2008

249 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/da2c39b27dacd9073861ab6d6b678d4811a138fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Revisions to PCE Inflation Measures: Implications for Monetary Policy (2008, unknown): “Aruoba (2008) found that most U.S. data revisions are neither pure news nor noise, as suggested by Mork.”
Multivariate singular spectrum analysis for forecasting revisions to real-time data (2011, background): “The issues raised in early contributions by Mankiw et al. [51], Mankiw and Shapiro [52] and Mork [54], in the news versus noise debate, continue to be relevant, see Aruoba [3].”
Macroeconomic Uncertainty Through the Lens of Professional Forecasters (2019, unknown): “The squared forecast errors are weighted by the loadings taken from a factor model estimated to construct a business condition index as in Aruoba et al. (2009). The most distinct feature of our approach is that it postulates a factor structure explicitly for an increasing set of survey forecast erro”
Real-Time Measurement of Business Conditions (2007, unknown): “Finally, the term premium is also strongly cyclical, as studied, for example, in Diebold, Rudebusch, and Aruoba (2006) and several of the papers they cite.”
Introducing the Euro-STING: Short Term INdicator of Euro Area Growth (2010, methodology): “To show that this is a reasonable assumption in our model, we develop the standard analysis (see Aruoba, 2008) of data revisions to the relationships between rst and second.4 First, we obtain that the mean of the revisions is statistically signi cant (p-value of 0.007), suggesting that the initial…”
Improving GDP Measurement: A Measurement-Error Perspective (2013, unknown): “Our work is related to, and complements, (Aruoba et al., 2012). There we took a forecast-error perspective, whereas here we take a measurement-error perspective.3 In particular, we work with a dynamic factor model in the tradition of Geweke (1977) and Sargent and Sims (1977), as used and extended by”
The on-the-run liquidity phenomenon (2009, methodology): “The above procedure is motivated by the observation that these revisions can be interpreted as noise since they are predictable based on past information (e.g., Mork, 1987; Faust, Rogers, and Wright, 2005; Aruoba, 2008).”
Information in the Revision Process of Real-Time Datasets (2008, unknown): “Aruoba (2008) finds that for most U.S. macroeconomic series, revision errors have a positive bias, and are highly predictable using information available at the time of their first release. The issue of news versus noise is also important for forecast evaluation. For example, Clark and McCracken (20”
Why do forecasters disagree? Lessons from the term structure of cross-sectional dispersion (2010, methodology): “We use the simulated method of moments (SMM), (Gourieroux and Monfort (1996a); Hall (2005)), to match the cross-sectional dispersion implied by our model, δ(2)h, with its sample equivalent in the data given in equation (4).”