Estimating Potential Output, Core Inflation, and the NAIRU as Latent Variables

Doménech, Rafael; Gómez, Víctor

doi:10.1198/073500105000000315

Cited by 45 publications

(35 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some applications include the estimation of regression models with time varying parameters as in Cooley and Prescott (1973), models with unobserved expectations of agents as Hamilton (1985), models with unobserved factors like in Engle and Watson (1981) for metropolitan wage prices or models with measurement errors like in Howrey (1984). There are also many applications in which the unobserved states are components with a direct interpretation; see, for example, Orphanides and van Norden (2002) and Doménech and Gómez (2006) for estimating unobserved the output gap in several economies, Pedregal and Young (2006) for electricity load demand with unobserved modulated periodic components, Stock and Watson (2007) for a trend-cycle model with stochastic volatility fitted to US inflation or Rueda and Rodríguez (2009) to estimate fertility rates, just to cite a few recent empirical applications. One of the main attractiveness of state space models is that they allow the estimation of the underlying states which, as the previous applications illustrate, are often of interest in themselves.…”

Section: Introductionmentioning

confidence: 99%

“…We build on previous work by Doménech and Gómez (2006) who propose a multivariate unobserved components model for the US economy with the four unobserved variables mentioned above.…”

Section: Introductionmentioning

confidence: 99%

“…Doménech and Gómez (2006) use the standard Kalman filter PMSE to construct prediction intervals for the NAIRU and conclude that it is an adequate indicator for predicting expansions and recessions. However, the intervals are wider when using the bootstrap methods, specially, when using the procedures proposed in this paper that take into account the added uncertainty due to the parameter estimation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bootstrap prediction mean squared errors of unobserved states based on the Kalman filter with estimated parameters

Rodríguez

Ruiz

2012

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

Prediction intervals in State Space models can be obtained by assuming Gaussian innovations and using the prediction equations of the Kalman filter, where the true parameters are substituted by consistent estimates. This approach has two limitations. First, it does not incorporate the uncertainty due to parameter estimation. Second, the Gaussianity assumption of future innovations may be inaccurate. To overcome these drawbacks, Wall and Stoffer (2002) propose to obtain prediction intervals by using a bootstrap procedure that requires the backward representation of the model. Obtaining this representation increases the complexity of the procedure and limits its implementation to models for which it exists. The bootstrap procedure proposed by Wall and Stoffer (2002) is further complicated by fact that the intervals are obtained for the prediction errors instead of for the observations. In this paper, we propose a bootstrap procedure for constructing prediction intervals in State Space models that does not need the backward representation of the model and is based on obtaining the intervals directly for the observations. Therefore, its application is much simpler, without loosing the good behavior of bootstrap prediction intervals. We study its finite sample properties and compare them with those of the standard and the Wall and Stoffer (2002) January 2010 AbstractIn the context of linear state space models with Gaussian errors and known parameters, the Kalman filter generates best linear unbiased predictions of the underlying components together with their corresponding prediction mean squared errors (PMSE). However, in practice, the filter is run by substituting some parameters of the model by consistent estimates. In these circumstances, the PMSEs given by the Kalman filter do not take into account the parameter uncertainty and, consequently, they underestimate the true PMSEs. In this paper, we propose two new bootstrap procedures to obtain PMSE of the unobserved states based on obtaining replicates of the underlying states conditional on the information available at each moment of time. By conditioning on the available information, we simplify the procedure with respect to alternative bootstrap proposals previously available in the literature. Furthermore, we show that the new procedures proposed in this paper have better finite sample properties than the alternatives. We implement the proposed procedures for estimating the PMSE of several key unobservable US macroeconomic variables as the output gap, the non accelerating inflation rate of unemployment (NAIRU), the long-run investment rate and the core inflation. We show how taking into account the parameter uncertainty may change the prediction intervals constructed for those unobservable macroeconomic variables and, in particular, change the conclusions about the utility of the NAIRU as a macroeconomic indicator for expansions and recessions.

show abstract

Section: Introductionmentioning

confidence: 99%

“…We build on previous work by Doménech and Gómez (2006) who propose a multivariate unobserved components model for the US economy with the four unobserved variables mentioned above.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bootstrap prediction mean squared errors of unobserved states based on the Kalman filter with estimated parameters

Rodríguez

Ruiz

2012

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

show abstract

“…If such an approach proves correct, it would be interesting to investigate in the future its similarities and differences versus standard output-gap theorem [Akerlof, Dickens, and Perry;Ball;Bardsen and Nymoen;Baxter and King;Betcherman;Beveridge and Nelson;Blanchard and Katz;Blanchflower and Oswald;Claus (2000a, b);Cochrane;Conway and Hunt;Denis, Mc Morrow, and Roger;Domenech and Gomez;Elmeskov and Mac Farlan;Estrella and Mishkin;Evans;Gerlach and Smets;Giorno, Richardson, Roseveare, and van der Noord;Gordon (1996Gordon ( , 1997Guarda;Herz and Roger;Holden;Kichian;Kuttner;Layard, Nickell, and Jackman;Logeay and Tober;Proietti, Mussoy, and Westermanny;Rennison;Room;Staiger, Stock and Watson;Stiglitz;Stockhammer].…”

Section: Chapter I: Macroeconomic Behavioural Relationshipsmentioning

confidence: 99%

Integration of Macroeconomic Behavioural Relationships and the Input-Output Block (Romanian Modelling Experience)

Dobrescu

2006

SSRN Journal

View full text Add to dashboard Cite

The last version of the Romanian macromodel (Dobrescu 2005b) incorporates the experience accumulated through the utilisation of its previous forms -either experimental (Dobrescu 1991(Dobrescu -1994 or operational (Dobrescu 1996(Dobrescu -2005a. At the same time, it introduces some methodological and informational improvements.The most significant of them is the structural decomposition of economy, according to the input-output techniques. Output and absorption are divided into: a) agriculture, sylviculture, forestry, hunting, and fishing; b) mining and energy; c) manufacturing industry; d) construction; e) transport, post and communications; f) trade and services. These categories can be easily translated into the classical three-sectors classification: primary (a+b), secondary (c+d), and tertiary (e+f).Due to the relatively advanced stage of the transitional processes in Romania, the behavioural functions were modelled -as much as possible -by the standard relationships. Besides, unlike the previous versions (that used statistical series beginning with 1980) the present one is based exclusively on information regarding the period 1989-2004.Since the input-output tables are defined yearly, the model contains only annual indicators. They are expressed in denominated local currency (RON). The export, import, and exchange rate series were transformed in Euro. When there were several informational sources for the same indicator, the data extracted or derived from national accounts have been adopted.The statistical series are relatively short and often fractured (because of the transforming processes of transition). Although, it is known that ADF test of stationarity does not offer reliable results in the case of limited number of observations, generally the series satisfying it were used. The simplest regression methods were also preferred. The structural breaks in evolution of some series have been dealt by the inclusion of dummies. Obviously, all these circumstances weaken the stability of econometric coefficients that must be continuously updated.The first two chapters of the paper characterise the main macroeconomic behavioural relationships and input-output coefficients. The third one discusses a possible scenario for the Romanian economy during [2005][2006][2007][2008][2009][2010]. A set of simulations is presented in the final part of the paper; these reveal some operational features of the macromodel.

show abstract

“…In the New Keynesian approach the Phillips curve is forward looking, as inflation depends on expected future inflation. Domenech and Gómez (2006) estimate a multivariate model of output fluctuations including a forward looking Phillips curve specified as follows: …”

Section: Bivariate Models Of Real Output and Inflationmentioning

confidence: 99%

Structural Time Series Models for Business Cycle Analysis

Proietti¹

2009

Palgrave Handbook of Econometrics

View full text Add to dashboard Cite

The chapter deals with parametric models for the measurement of the business cycle in economic time series. It presents univariate methods based on parametric trend-cycle decompositions and multivariate models featuring a Phillips type relationship between the output gap and inflation and the estimation of the gap using mixed frequency data. We finally address the issue of assessing the accuracy of the output gap estimates.

show abstract

Estimating Potential Output, Core Inflation, and the NAIRU as Latent Variables

Cited by 45 publications

References 27 publications

Bootstrap prediction mean squared errors of unobserved states based on the Kalman filter with estimated parameters

Bootstrap prediction mean squared errors of unobserved states based on the Kalman filter with estimated parameters

Integration of Macroeconomic Behavioural Relationships and the Input-Output Block (Romanian Modelling Experience)

Structural Time Series Models for Business Cycle Analysis

Contact Info

Product

Resources

About