Results 1  10
of
28
Nowcasting is not just contemporaneous forecasting
 National Institute Economic Review
, 2009
"... We consider the reasons for nowcasting, the timing of information and sources thereof, especially contemporaneous data, which introduce different aspects compared to forecasting. We allow for the impact of location shifts inducing nowcast failure and nowcasting during breaks, probably with measurem ..."
Abstract

Cited by 12 (4 self)
 Add to MetaCart
We consider the reasons for nowcasting, the timing of information and sources thereof, especially contemporaneous data, which introduce different aspects compared to forecasting. We allow for the impact of location shifts inducing nowcast failure and nowcasting during breaks, probably with measurement errors. We also apply a variant of the nowcasting strategy proposed in Castle and Hendry (2009) to nowcast Euroarea GDP growth. Models of disaggregate monthly indicators are built by automatic methods, forecasting all variables that are released with a publication lag each period, then testing for shifts in available measures including survey data, switching to robust forecasts of missing series when breaks are detected.
Econometric model selection with more variables than observations. Working paper
"... Preliminary version Several algorithms for indicator saturation are compared and found to have low power when there are multiple breaks. A new algorithm is introduced, based on repeated application of an automatic model selection procedure (Autometrics, see Doornik, 2009) which is based on the gener ..."
Abstract

Cited by 11 (2 self)
 Add to MetaCart
Preliminary version Several algorithms for indicator saturation are compared and found to have low power when there are multiple breaks. A new algorithm is introduced, based on repeated application of an automatic model selection procedure (Autometrics, see Doornik, 2009) which is based on the generaltospecific approach. The new algorithm can also be applied in the general case of more variables than observations. The performance of this new algorithm is investigated through Monte Carlo analysis. The relationship between indicator saturation and robust estimation is explored. Building an the results of Johansen and Nielsen (2009), the asymptotic distribution of multistep indicator saturation is derived, as well as the efficiency of the twostep variance. Next, the asymptotic distribution of multistep robust estimation using two different critical values (a low one at first) is derived. The asymptotic distribution of the fully iterated case is conjectured, as is the asymptotic distribution of reweighted least squares based on least trimmed squares (Rousseeuw, 1984)), called RLTS here. This allows for a comparison of the efficiency of indicator saturation with RLTS. Finally, the performance of several robust estimators and the new approach is studied in the presence of a structural break. When there are many irrelevant regressors in the model, the robust estimators break down while the new algorithm is largely unaffected. 1
Econometric modelling of time series with outlying observations
, 2010
"... Economies are buffeted by natural shocks, wars, policy changes, and other unanticipated events. Observed data can be subject to substantial revisions. Consequently, a ‘correct ’ theory can manifest serious misspecification if just fitted to data ignoring its timeseries characteristics. Modelling U ..."
Abstract

Cited by 8 (6 self)
 Add to MetaCart
Economies are buffeted by natural shocks, wars, policy changes, and other unanticipated events. Observed data can be subject to substantial revisions. Consequently, a ‘correct ’ theory can manifest serious misspecification if just fitted to data ignoring its timeseries characteristics. Modelling US expenditure on food, the simplest theory implementation fails to describe the evidence. Embedding that theory in a general framework with dynamics, outliers and structural breaks, using impulseindicator saturation, the selected model performs well, despite commencing with more variables than observations (see Doornik, 2009b), producing useful robust forecasts. Although this illustration involves a simple theory, the implications are generic and apply to sophisticated theories.
Automatic selection of nonlinear models
 System Identification, Environmental Modelling and Control, forthcoming
, 2010
"... Our strategy for automatic selection in potentially nonlinear processes is: test for nonlinearity in the unrestricted linear formulation; if that test rejects, specify a general model using polynomials, to be simplified to a minimal congruent representation; finally select by encompassing tests of ..."
Abstract

Cited by 7 (7 self)
 Add to MetaCart
(Show Context)
Our strategy for automatic selection in potentially nonlinear processes is: test for nonlinearity in the unrestricted linear formulation; if that test rejects, specify a general model using polynomials, to be simplified to a minimal congruent representation; finally select by encompassing tests of specific nonlinear forms against the selected model. Nonlinearity poses many problems: extreme observations leading to nonnormal (fattailed) distributions; collinearity between nonlinear functions; usually more variables than observations when approximating the nonlinearity; and excess retention of irrelevant variables; but solutions are proposed. A returnstoeducation empirical application demonstrates the feasibility of the nonlinear automatic model selection algorithm Autometrics.
Model Discovery and Trygve Haavelmo’s Legacy
"... Trygve Haavelmo’s Probability Approach aimed to implement economic theories, but he later recognized their incompleteness. Although he did not explicitly consider model selection, we apply it when theoryrelevant variables,{xt}, are retained without selection while selecting other candidate variable ..."
Abstract

Cited by 7 (3 self)
 Add to MetaCart
Trygve Haavelmo’s Probability Approach aimed to implement economic theories, but he later recognized their incompleteness. Although he did not explicitly consider model selection, we apply it when theoryrelevant variables,{xt}, are retained without selection while selecting other candidate variables, {wt}. Under the null that the {wt} are irrelevant, by orthogonalizing with respect to the {xt}, the estimator distributions of the xt’s parameters are unaffected by selection even for more variables than observations and for endogenous variables. Under the alternative, when the joint model nests the generating process, an improved outcome results from selection. This implements Haavelmo’s program relatively costlessly.
2011): “Forecasting Breaks and Forecasting During Breaks
 in Oxford Handbook of Economic Forecasting
"... Success in accurately forecasting breaks requires that they are predictable from relevant information available at the forecast origin using an appropriate model form, which can be selected and estimated before the break. To clarify the roles of these six necessary conditions, we distinguish betwee ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
Success in accurately forecasting breaks requires that they are predictable from relevant information available at the forecast origin using an appropriate model form, which can be selected and estimated before the break. To clarify the roles of these six necessary conditions, we distinguish between the information set for ‘normal forces ’ and the one for ‘break drivers’, then outline sources of potential information. Relevant nonlinear, dynamic models facing multiple breaks can have more candidate variables than observations, so we discuss automatic model selection. As a failure to accurately forecast breaks remains likely, we augment our strategy by modelling breaks during their progress, and consider robust forecasting devices. JEL classifications: C1, C53.
2013): “Testing for Structural Stability of Factor Augmented Forecasting Models
 Journal of Econometrics
"... 1 Mild factor loading instability, particularly if sufficiently independent across the different constituent variables, does not affect the estimation of the number of factors, nor subsequent estimation of the factors themselves (see e.g. Stock and Watson (2009)). This result does not hold in the p ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
1 Mild factor loading instability, particularly if sufficiently independent across the different constituent variables, does not affect the estimation of the number of factors, nor subsequent estimation of the factors themselves (see e.g. Stock and Watson (2009)). This result does not hold in the presence of large common breaks in the factor loadings, however. In this case, information criteria overestimate the number of breaks. Additionally, estimated factors are no longer consistent estimators of “true ” factors. Hence, various recent research papers in the diffusion index literature focus on testing the constancy of factor loadings. One reason why this is a positive development is that in applied work, factor augmented forecasting models are used widely for prediction, and it is important to understand when such models are stable. Now, forecast failure of factor augmented
Semiautomatic Nonlinear Model Selection
, 2013
"... We consider model selection for nonlinear dynamic equations with more candidate variables than observations, based on a general class of nonlinearinthevariables functions, addressing possible location shifts by impulseindicator saturation. After an automatic search delivers a simplified congru ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
We consider model selection for nonlinear dynamic equations with more candidate variables than observations, based on a general class of nonlinearinthevariables functions, addressing possible location shifts by impulseindicator saturation. After an automatic search delivers a simplified congruent terminal model, an encompassing test can be implemented against an investigator’s preferred nonlinear function. When that is nonlinear in the parameters, such as a threshold model, the overall approach can only be semiautomatic. The method is applied to reanalyze an empirical model of real wages in the UK over 1860–2004, updated and extended to 2005–2011 for forecast evaluation.
2011): «Empirical Economic Model Discovery and Theory Evaluation
, 2011
"... Abstract Economies are so high dimensional and nonconstant that many features of models cannot be derived by prior reasoning, intrinsically involving empirical discovery and requiring theory evaluation. Despite important differences, discovery and evaluation in economics are similar to those of sc ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract Economies are so high dimensional and nonconstant that many features of models cannot be derived by prior reasoning, intrinsically involving empirical discovery and requiring theory evaluation. Despite important differences, discovery and evaluation in economics are similar to those of science. Fitting a prespecified equation limits discovery, but automatic methods can formulate much more general models with many variables, long lag lengths and nonlinearities, allowing for outliers, data contamination, and parameter shifts; select congruent parsimoniousencompassing models even with more candidate variables than observations, while embedding the theory; then rigorously evaluate selected models to ascertain their viability. JEL classifications: C18, B40.
Unpredictability in Economic Analysis, Econometric Modeling and Forecasting
"... Unpredictability arises from intrinsic stochastic variation, unexpected instances of outliers, and unanticipated extrinsic shifts of distributions. We analyze their properties, relationships, and different effects on the three arenas in the title, which suggests considering three associated informat ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
Unpredictability arises from intrinsic stochastic variation, unexpected instances of outliers, and unanticipated extrinsic shifts of distributions. We analyze their properties, relationships, and different effects on the three arenas in the title, which suggests considering three associated information sets. The implications of unanticipated shifts for forecasting, economic analyses of efficient markets, conditional expectations, and intertemporal derivations are described. The potential success of generaltospecific model selection in tackling location shifts by impulseindicator saturation is contrasted with the major difficulties confronting forecasting.