Drifts and volatilities under measurement error: Assessing monetary policy shocks over the last century

Abstract

How much have the dynamics of U.S. time series changed over the last century? Has the evolution of the Federal Reserve as an institution over the 100 years altered the transmission of monetary policy shocks? To tackle these questions, we build a multivariate time series model with time-varying parameters and stochastic volatility that features measurement errors in observables. We find substantial changes in the structure of the economy. There is also large variation in the impact of monetary policy shocks, but the majority of this variation is driven by changes in exogenous volatility.

Beveridge Curve Shifts and Time-Varying Parameter VARs

“…It thus may very well be that the posterior sampler in the Bayesian estimation attributes this type of variation in the data to residual shocks, just as a …xed-coe¢ cient VAR would. What supports this argument is that during times of economic upheaval, chie ‡y the Great Depression period, TVP-VARs do tend to exhibit considerable time variation in the lag coe¢ cients (Benati and Lubik 2014;Amir-Ahmadi, Matthes, and Wang 2016). That said, we argue that the basic point still applies as to the interpretability of TVP-VAR results.…”

“…It is well-known that inference under heteroskedasticity (or time variation in the innovation covariance matrix) is quite problematic in short sample (e.g., Toyoda 1974). For that reason, TVP-VARs generally perform better in longer samples, as in Amir-Ahmadi, Matthes, and Wang (2016). A second aspect is that in models with many parameters, the choice of priors can be very important.…”

Monetary policy, external instruments, and heteroskedasticity

“…A common feature of macroeconomic and financial data are changes in volatility over time (see, among others, Stock and Watson (2002), Justiniano and Primiceri (2008), Amir‐Ahmadi, Matthes, and Wang (2016)). Rigobon and Sack (2004), Normandin and Phaneuf (2004), and Lanne and Lütkepohl (2008) show that this holds in particular for the analysis of monetary policy where changes in volatility of the data feed into heteroskedastic residuals in monetary SVARs and can be used for identification.…”

“…We use our framework to evaluate the validity of instruments proposed in the literature and to provide new, and in light of the Monte Carlo evidence, sharper estimates of the macroeconomic effects of monetary policy shocks in the United States based on heteroskedasticity and a valid instrument. The former is a common and well‐documented feature of U.S. real and financial data (Stock and Watson (2002), Justiniano and Primiceri (2008), Amir‐Ahmadi, Matthes, and Wang (2016)). Standard statistics provide strong evidence that changes in volatility are also present in our sample.…”

Stock markets, banks and economic growth in the UK, 1850–1913

“… 25 Straumann and Woitek (2009); Kliem et al (2016); Amir-Ahmadi et al (2016); Keating and Valcarcel (2015); Bijsterbosch and Falagiarda (2015); Gambetti and Musso (2017). …”