Inflation uncertainty revisited: a proposal for robust measurement

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractAny measure of unobserved inflation uncertainty relies on specific assumptions which are most likely not fulfilled completely. This calls into question whether an individual measure delivers a reliable signal. To reduce idiosyncratic measurement error, we propose using common information contained in different measures derived from survey data, a variety of forecast models, and volatility models. We show that all measures are driven by a common component which constitutes an indicator for inflation uncertainty. Moreover, the idiosyncratic component of survey disagreement contains systematic measurement error during economic downturns. Finally, we study the Friedman-Ball hypothesis. Using the indicator, it turns out that higher inflation is followed by higher uncertainty. By contrast, we obtain contradictory results for the individual measures. We also document that, after an inflationary shock, uncertainty decreases in the first two months which is traceable to the energy component in CPI inflation.JEL Code: C53, E31, E37.

Dimensions of Macroeconomic Uncertainty: A Common Factor Analysis

“…We consider a data‐driven filter to approximate the conditional volatility which is known as the RiskMetrics procedure (JP Morgan/Reuters 1996). This measure is similar to the conditional volatility of GARCH models which measures the forecast uncertainty in sample, that is, prevailing at the time (see Baillie, Chung, and Tieslau ; Grier and Perry ; Grimme, Henzel, and Wieland ; Lahiri and Sheng , among others) . The objective is to calculate an exponentially weighted moving average of the squared (in‐sample) forecast errors of an appropriately defined forecast model.…”

“…However, surveys are limited to selected variables such as gross domestic product (GDP), GDP deflator, and consumer price index (CPI) inflation and, thus, these approaches are not suited to measure general macroeconomic uncertainty. This measure is similar to the conditional volatility of GARCH models which measures the forecast uncertainty in sample, that is, prevailing at the time (see Baillie, Chung, and Tieslau 1996;Grier and Perry 1998;Grimme, Henzel, and Wieland 2014;Lahiri and Sheng 2010, among others). 4 The objective is to calculate an exponentially weighted moving average of the squared (in-sample) forecast errors of an appropriately defined forecast model.…”

Global and Country‐Specific Output Growth Uncertainty and Macroeconomic Performance

“…The two approaches most frequently utilized are stochastic volatility and GARCH models. Although there appears to be a proliferation of the latter, both approaches have been shown to yield comparable results relative to survey‐based measures of inflation and output growth uncertainty (see Chua, Kim and Suardi, ; Grimme, Henzel and Wieland, ). However, whereas the volatility process in GARCH models is explained solely in terms of level changes, stochastic volatility models are more flexible as they allow for a separate innovation impinging on volatility, independent of any changes in levels (Fernández‐Villaverde and Rubio‐Ramírez, ).…”

Time-Frequency Relationship between Inflation and Inflation Uncertainty for the U.S.: Evidence from Historical Data

“…Second, we rely on the use of a novel method for the uncertainty's assessment, proposed by Chan et al (2013). In contrast to the literature that associates inflation uncertainty with its variance and employs different generalized autoregressive conditional heteroskedasticity (GARCH)-type models, or to the literature that uses the Stock and Watson's (2007) time-varying approach, we employ the bounded model recently proposed by Chan et al (2013), which ensures that the trend inflation lies in a specific interval (for a review of the literature on inflation uncertainty assessment, see Grimme et al, 2014). This approach proves particularly appealing for measuring uncertainty in inflation-targeting periods.…”