Predictable non-linearities in U.S. inflation

Binner, Jane M.; Elger, C. Thomas; Nilsson, Bo; Tepper, Jonathan

doi:10.1016/j.econlet.2006.06.001

Cited by 27 publications

(25 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common finding with RS-VAR models is that allowing for different intercepts in each regime, while leaving the dynamic structure unchanged across regimes, provides the best models for forecasting purposes. See Binner et al (2004Binner et al ( , 2006 for relevant empirical findings with respect to inflation forecasting. 22 In particular, Binner et al (2004) find that the forecasting performance of their model deteriorated when regime-switching dynamic structure was included, which they attribute to in-sample over fitting.…”

Section: Empirical Analysismentioning

confidence: 99%

“…For the RS-VAR models, we assume an underlying homogenous discrete Markov chain with two states (s = 2). Following Binner et al (2004Binner et al ( , 2006, the intercepts and the variance-covariance matrix are allowed to switch between the two states while all autoregressive parameters are equal across states. A common finding with RS-VAR models is that allowing for different intercepts in each regime, while leaving the dynamic structure unchanged across regimes, provides the best models for forecasting purposes.…”

Section: Empirical Analysismentioning

confidence: 99%

See 1 more Smart Citation

Forecasting with Monetary Aggregates: Recent Evidence for the United States

Elger

Jones

Nilsson

2006

Journal of Economics and Business

Self Cite

View full text Add to dashboard Cite

Section: Empirical Analysismentioning

confidence: 99%

Section: Empirical Analysismentioning

confidence: 99%

Forecasting with Monetary Aggregates: Recent Evidence for the United States

Elger

Jones

Nilsson

2006

Journal of Economics and Business

Self Cite

View full text Add to dashboard Cite

“…Consider choosing a vector of fixed parameters, β so as to solve We build upon our previous successes with RNNs, (Binner et al, , 2006 for modeling financial time-series data and extend our RNN models to a subset of RNNs referred to as multi-recurrent networks (MRNs) (Ulbricht, 1994;Dorffner, 1996). The MRN architecture combines several types of feedback and delay to form a state-based model whose state transitions are modeled as an extended nonlinear auto-regressive moving average (ARMA) process (Dorffner, 1996).…”

Section: Methodologiesmentioning

confidence: 99%

Does Money Matter in Inflation Forecasting?

Anderson¹,

Tiňo²,

Tepper³

et al. 2009

Self Cite

View full text Add to dashboard Cite

This paper provides the most fully comprehensive evidence to date on whether or not monetary aggregates are valuable for forecasting US inflation in the early to mid 2000s. We explore a wide range of different definitions of money, including different methods of aggregation and different collections of included monetary assets. In our forecasting experiment we use two non-linear techniques, namely, recurrent neural networks and kernel recursive least squares regression-techniques that are new to macroeconomics. Recurrent neural networks operate with potentially unbounded input memory, while the kernel regression technique is a finite memory predictor. The two methodologies compete to find the best fitting US inflation forecasting models and are then compared to forecasts from a naive random walk model. The best models were non-linear autoregressive models based on kernel methods. Our findings do not provide much support for the usefulness of monetary aggregates in forecasting inflation. Beyond its economic findings, our study is in the tradition of physicists' long-standing interest in the interconnections among statistical mechanics, neural networks, and related nonparametric statistical methods, and suggests potential avenues of extension for such studies.

show abstract

“…In recent years, researchers have begun to study the dynamic behavior of the inflation rate by employing nonlinear models. For example, threshold autoregressive models are applied by Enders and Hurn (2002) in the study on the dynamic characteristics of the inflation rate, Bidarkota (2001) and Binner et al (2006) apply the Markov regime switching models, and Arghyrou (2005) and Nobay et al (2010) employ smooth transition autoregressive models (STAR).…”

Section: Introductionmentioning

confidence: 99%