Autoregression-based estimation of the new Keynesian Phillips curve

Abstract

We propose an estimation method of the new Keynesian Phillips curve (NKPC) based on a univariate noncausal autoregressive model for the inflation rate. By construction, our approach avoids a number of problems related to the GMM estimation of the NKPC. We estimate the hybrid NKPC with quarterly U.S. data (1955:1--2010:3), and both expected future inflation and lagged inflation are found important in determining the inflation rate, with the former clearly dominating. Moreover, inflation persistence turns out to be intrinsic rather than inherited from a persistent driving process.JEL Classification: C22, C51, E31

On inflation expectations in the NKPC model

“…See equation (4) in Lanne and Luoto (2013). To estimate the parameters in this NKPC model, one needs to replace the unobserved variable E t π t+1 by an observable variable.…”

“…With this assumption, Lanne and Luoto (2013) use Maximum Likelihood to estimate the parameters in (2). There is, however, a problem with this approach.…”

“…In one part of the literature on the NKPC, notably Lanne and Luoto (2013), Gali and Gertler (1999), and Gali et al (2005), among others, a key assumption is rational expectations. There it is commonly assumed that the expected value of next year's inflation is equal to the realized value of inflation in the next year plus the forecast error for next year.…”

A Noncausal Autoregressive Model with Time-Varying Parameters: An Application to U.S. Inflation

“…In addition to estimation and forecasting in the unrestricted noncausal AR model with time-varying parameters, we also consider the estimation of the new Keynesian Phillips curve (NKPC) based on the new model, by placing additional restrictions along the lines of Lanne and Luoto (2013), who used a noncausal AR model with constant parameters to this end. A central problem in the estimation of the NKPC is that the model depends on an unobserved marginal cost variable that is di¢ cult to measure, but estimation based on the noncausal AR model has the advantage that no marginal cost proxy is needed, but the variable is latent.…”

“…A central problem in the estimation of the NKPC is that the model depends on an unobserved marginal cost variable that is di¢ cult to measure, but estimation based on the noncausal AR model has the advantage that no marginal cost proxy is needed, but the variable is latent. However, assuming constancy of the parameters of the AR model, as in Lanne and Luoto (2013), leads to ignoring the e¤ect of structural breaks due to technological changes, among other things, that may have taken place over time. Therefore, it is interesting to see, to what extent having time-varying parameters in the AR model a¤ects the general conclusions.…”