Mark Bognanni

We develop a sequential Monte Carlo (SMC) algorithm for Bayesian inference in vector autoregressions with stochastic volatility (VAR-SV). The algorithm builds particle approximations to the sequence of the model’s posteriors, adapting the particles from one approximation to the next as the window of available data expands. The parallelizability of the algorithm’s computations allows the adaptations to occur rapidly. Our particular algorithm exploits the ability to marginalize many parameters from the posterior analytically and embeds a known Markov chain Monte Carlo (MCMC) algorithm for the model as an effective mutation kernel for fighting particle degeneracy. We show that, relative to using MCMC alone, our algorithm increases the precision of inference while reducing computing time by an order of magnitude when estimating a medium-scale VAR-SV model.

This paper develops a new class of structural vector autoregressions (SVARs) with time-varying parameters, which I call a drifting SVAR (DSVAR). The DSVAR is the first structural time-varying parameter model to allow for internally consistent probabilistic inference under exact—or set—identification, nesting the widely used SVAR framework as a special case. I prove that the DSVAR implies a reduced-form representation, from which structural inference can proceed similarly to the widely used two-step approach for SVARs: beginning with estimation of a reduced form and then choosing among observationally equivalent candidate structural parameters via the imposition of identifying restrictions. In a special case, the implied reduced form is a tractable known model for which I provide the first algorithm for Bayesian estimation of all free parameters. I demonstrate the framework in the context of Baumeister and Peersman’s (2013b) work on time variation in the elasticity of oil demand.

We document the effectiveness of Sequential Monte Carlo algorithms at estimating MSVAR posteriors, and we show that the use of priors with superior data fit alters inference about the presence of time variation in macroeconomic dynamics.

This article explores the potential for market-based inflation measures to improve inflation forecasting. To do so, I compare the pseudo-real time forecasting performance of a suite of models for forecasting total or “headline” PCE inflation over the short and medium run. In the forecasting exercise, a simple model using only market-based core PCE inflation showed the best forecasting performance at all horizons.

Economic data are routinely revised after they are initially released. I examine the extent to which the real-time reliability of six monthly macroeconomic indicators important to policymakers has remained stable over time by studying the time-series properties of their short-term and long-term revisions. I show that the revisions to many monthly economic indicators display systematic behaviors that policymakers could build into their real-time assessments. I also find that some indicators’ revision series have varied substantially over time, suggesting that these indicators may now be less useful in real time than they once were. Lastly, I find that substantial revisions tend to occur indefinitely after the initial data release, a result which suggests a certain degree of caution is in order when using even thrice-revised monthly data in policymaking.

The Institute for Supply Management produces a measure of pricing trends, the manufacturing price index or ISMPI, that is constructed from its periodic surveys of purchasing and supply executives. We investigate this measure’s predictive content for producer and consumer price inflation by assessing its ability to improve inflation forecasts for three broad monthly inflation measures. We find that the ISMPI has some predictive content for producer prices but not for consumer prices.

We study labor productivity between 1968 and 2016 and compare recent productivity growth to its past behavior. We find that though recent productivity data are unambiguously weak, they are not greatly out of line with the variation of productivity over the historical record. We find that when labor productivity has been weak in the past, it did not persist at those levels. In addition, we find a systematic tendency to understate growth in real time, suggesting that the average rate of the past six years will likely be revised up in future.