Posterior‐predictive Evidence on Us Inflation Using Extended New Keynesian Phillips Curve Models With Non‐filtered Data

Abstract

SUMMARYChanging time series properties of US inflation and economic activity, measured as marginal costs, are modeled within a set of extended New Keynesian Phillips curve (NKPC) models. It is shown that mechanical removal or modeling of simple low‐frequency movements in the data may yield poor predictive results which depend on the model specification used. Basic NKPC models are extended to include structural time series models that describe typical time‐varying patterns in levels and volatilities. Forward‐ and backward‐looking expectation components for inflation are incorporated and their relative importance is evaluated. Survey data on expected inflation are introduced to strengthen the information in the likelihood. Use is made of simulation‐based Bayesian techniques for the empirical analysis. No credible evidence is found on endogeneity and long‐run stability between inflation and marginal costs. Backward‐looking inflation appears stronger than forward‐looking inflation. Levels and volatilities of inflation are estimated more precisely using rich NKPC models. The extended NKPC structures compare favorably with existing basic Bayesian vector autoregressive and stochastic volatility models in terms of fit and prediction. Tails of the complete predictive distributions indicate an increase in the probability of deflation in recent years. Copyright © 2014 John Wiley & Sons, Ltd.

An Inflation‐Predicting Measure of the Output Gap in the Euro Area

“…Planas, Rossi, and Fiorentini (2008) estimate a Bayesian version of Kuttner's model and we build on their priors. Similar to Baştürk et al (2014), we use nonfiltered data and pay much attention to modeling their low-frequency behavior. We confirm the finding of Valle e Azevedo, Koopman, and Rua (2006) and Basistha and Startz (2008) that using multiple real activity indicators increases the reliability of output gap estimates.…”

A New Time‐Varying Parameter Autoregressive Model for U.S. Inflation Expectations

“…However, as recently shown by Baştürk et al. (), a priori data filtering affects the posterior inference on the structural NKPC parameters and may yield poor predictive results. In contrast to the approach of Lanne and Luoto (), estimation of the NKPC based on the TVP‐AR model (1) facilitates estimation of mean inflation jointly with the structural parameters and .…”

“…It is important to emphasize that while keeping the structural parameters constant, we allow for time variation in the mean to capture the continuous level shifts observed in the U.S. inflation data (see Baştürk et al. , and the references therein, for a detailed discussion on the assumption of the constancy of and in equation ). Hence, our approach yields an estimate of the trend inflation , in addition to facilitating evaluation of the relative importance of inflation expectations and lagged inflation in the NKPC.…”

Factor‐Based Identification‐Robust Interference in IV Regressions

“…See Basturk et al . () for a recent perspective on filtering. With non‐rejected specifications, we note that a zero value for the coefficient of driving variables in all three equations, except when it is restricted out as in the Galí et al . () model, cannot be refuted even when the estimated confidence set is tight.…”