Abstract

AbstractThis study considers Bayesian variable selection in the Phillips curve context by using the Bernoulli approach of Korobilis (Journal of Applied Econometrics, 2013, 28(2), 204–230). The Bernoulli model, however, is unable to account for model change over time, which is important if the set of relevant predictors changes. To tackle this problem, this paper extends the Bernoulli model by introducing a novel modeling approach called Markov dimension switching (MDS). MDS allows the set of predictors to change over time. It turns out that only a small set of predictors is relevant and that the relevant predictors exhibit a sizable degree of time variation for which the Bernoulli approach is not able to account, stressing the importance and benefit of the MDS approach. In addition, this paper provides empirical evidence that allowing for changing predictors over time is crucial for forecasting inflation.

Highlights

  • The Phillips curve has served as an important tool in macroeconomics for explaining and forecasting inflation in the U.S over the past five decades

  • The Bernoulli model, is unable to account for model change over time, which is important if the set of relevant predictors changes over time

  • While the original Phillips curve is likely to miss some important predictors, a generalized Phillips curve which uses too many predictors may lead to overfitting the data and to imprecise outof-sample predictions

Read more

Summary

Introduction

The Phillips curve has served as an important tool in macroeconomics for explaining and forecasting inflation in the U.S over the past five decades. The importance of changing predictors over time is documented by, inter alia, Stock and Watson (2010), who find that most predictors for inflation improve forecast performance only in some specific time periods. In the MDS model each indicator follows a Markov-switching process and allows for changing predictors over time. This approach allows for the calculation of timevarying variable inclusion probabilities to shed light on the question which variables are. Important in determining inflation at different times Both the Bernoulli and the MDS approach are used to assess the importance of the predictors for one quarter and one year inflation.

Markov Dimension Switching
Gibbs Sampler
Comparison with existing literature
Forecasting Inflation
Out-of-sample Results
Full sample results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call