Recent Developments in Modelling Nonstationary Vector Autoregressions

In this paper we review some recent developments in the modelling of nonstationary vector autoregressions (VARs) which we feel have great potential for furthering applied researchers understanding of the relationships linking the variables making up a VAR. The developments surveyed are the use of model determination criteria in selecting lag length, trend order and cointegrating rank, causality testing in vector error correction models, FM-VAR estimation of levels VARS, common trends and cycles analysis, permanent and transitory decompositions, impulse response asymptotics, and the links between cointegrated VARs and structural models. The techniques are illustrated by applications to the modelling of U.K. equities, dividends and interest rates.     

Automated Model Selection in Finance: General‐to‐Specific Modelling of the Mean and Volatility Specifications*

General‐to‐Specific (GETS) modelling has witnessed major advances thanks to the automation of multi‐path GETS specification search. However, the estimation complexity associated with financial models constitutes an obstacle to automated multi‐path GETS modelling in finance. Making use of a recent result we provide and study simple but general and flexible methods that automate financial multi‐path GETS modelling. Starting from a general model where the mean specification can contain autoregressive terms and explanatory variables, and where the exponential volatility specification can include log‐ARCH terms, asymmetry terms, volatility proxies and other explanatory variables, the algorithm we propose returns parsimonious mean and volatility specifications.     

Model specification test with correlated but not cointegrated variables

Many macroeconomic and financial variables show highly persistent and correlated patterns but are not necessarily cointegrated. Recently,  Sun et al. (2011) propose using a semiparametric varying coefficient approach to capture correlations between integrated but non cointegrated variables. Due to the complication arising from the integrated disturbance term and the semiparametric functional form, consistent estimation of such a semiparametric model requires stronger conditions than usually needed for consistent estimation for a linear (spurious) regression model, or a semiparametric varying coefficient model with a stationary disturbance. Therefore, it is important to develop a testing procedure to examine for a given data set, whether linear relationship holds or not, while allowing for the disturbance being an integrated process. In this paper we propose two test statistics for detecting linearity against semiparametric varying coefficient alternative specification. Monte Carlo simulations are used to examine the finite sample performances of the proposed tests.     

Moment-based estimation of smooth transition regression models with endogenous variables

Nonlinear regression models have been widely used in practice for a variety of time series and cross-section datasets. For purposes of analyzing univariate and multivariate time series data, in particular, smooth transition regression (STR) models have been shown to be very useful for representing and capturing asymmetric behavior. Most STR models have been applied to univariate processes, and have made a variety of assumptions, including stationary or cointegrated processes, uncorrelated, homoskedastic or conditionally heteroskedastic errors, and weakly exogenous regressors. Under the assumption of exogeneity, the standard method of estimation is nonlinear least squares. The primary purpose of this paper is to relax the assumption of weakly exogenous regressors and to discuss moment-based methods for estimating STR models. The paper analyzes the properties of the STR model with endogenous variables by providing a diagnostic test of linearity of the underlying process under endogeneity, developing an estimation procedure and a misspecification test for the STR model, presenting the results of Monte Carlo simulations to show the usefulness of the model and estimation method, and providing an empirical application for inflation rate targeting in Brazil. We show that STR models with endogenous variables can be specified and estimated by a straightforward application of existing results in the literature.     

Permanent-transitory Decomposition in Var Models With Cointegration and Common Cycles

In this paper we derive permanent-transitory decompositions of non-stationary multiple times series generated by (r)nite order Gaussian VAR(p) models with both cointegration and serial correlation common features. We extend existing analyses to the two classes of reduced rank structures discussed in Hecq, Palm and Urbain (1998). Using the corresponding state space representation of cointegrated VAR models in vector error correction form we show how decomposition can be obtained even in the case where the number of common feature and cointegration vectors are not equal to the number of variables. As empirical analysis of US business fluctuations shows the practical relevance of the approach we propose.     

Measuring correlations of integrated but not cointegrated variables: A semiparametric approach

Many macroeconomic and financial variables are integrated of order one (or I(1)) processes and are correlated with each other but not necessarily cointegrated. In this paper, we propose to use a semiparametric varying coefficient approach to model/capture such correlations. We propose two consistent estimators to study the dependence relationship among some integrated but not cointegrated time series variables. Simulations are used to examine the finite sample performances of the proposed estimators.     

Simple Identification and Specification of Cointegrated Varma Models

We bring together some recent advances in the literature on vector autoregressive moving‐average models, creating a simple specification and estimation strategy for the cointegrated case. We show that in this case with fixed initial values there exists a so‐called final moving‐average representation. We prove that the specification strategy is consistent. The performance of the proposed method is investigated via a Monte Carlo study and a forecasting exercise for US interest rates. We find that our method performs well relative to alternative approaches for cointegrated series and methods which do not allow for moving‐average terms. Copyright © 2014 John Wiley & Sons, Ltd.     

Bridging the Gap between Different Statistical Approaches: An Integrated Framework for Modelling

This paper proposes a template for modelling complex datasets that integrates traditional statistical modelling approaches with more recent advances in statistics and modelling through an exploratory framework. Our approach builds on the well-known and long standing traditional idea of 'good practice in statistics' by establishing a comprehensive framework for modelling that focuses on exploration, prediction, interpretation and reliability assessment, a relatively new idea that allows individual assessment of predictions.
The integrated framework we present comprises two stages. The first involves the use of exploratory methods to help visually understand the data and identify a parsimonious set of explanatory variables. The second encompasses a two step modelling process, where the use of non-parametric methods such as decision trees and generalized additive models are promoted to identify important variables and their modelling relationship with the response before a final predictive model is considered. We focus on fitting the predictive model using parametric, non-parametric and Bayesian approaches.
This paper is motivated by a medical problem where interest focuses on developing a risk stratification system for morbidity of 1,710 cardiac patients given a suite of demographic, clinical and preoperative variables. Although the methods we use are applied specifically to this case study, these methods can be applied across any field, irrespective of the type of response.     

Multivariate Small Area Estimation of Multidimensional Latent Economic Well-being Indicators

Factor analysis models are used in data dimensionality reduction problems where the variability among observed variables can be described through a smaller number of unobserved latent variables. This approach is often used to estimate the multidimensionality of well-being. We employ factor analysis models and use multivariate empirical best linear unbiased predictor (EBLUP) under a unit-level small area estimation approach to predict a vector of means of factor scores representing well-being for small areas. We compare this approach with the standard approach whereby we use small area estimation (univariate and multivariate) to estimate a dashboard of EBLUPs of the means of the original variables and then averaged. Our simulation study shows that the use of factor scores provides estimates with lower variability than weighted and simple averages of standardised multivariate EBLUPs and univariate EBLUPs. Moreover, we find that when the correlation in the observed data is taken into account before small area estimates are computed, multivariate modelling does not provide large improvements in the precision of the estimates over the univariate modelling. We close with an application using the European Union Statistics on Income and Living Conditions data.     

General-to-specific or specific-to-general modelling? An opinion on current econometric terminology

It is argued that what is the dominant approach to analyzing systems of cointegrated variables is not well described as general-to-specific (gets) modelling. The gets approach was developed during the last decades predominantly in a single equation framework. For multivariate modelling and especially cointegration analysis the leading approach is better classified as bottom-up or specific-to-general (spec) modelling.     

Nonlinear minimization estimators in the presence of cointegrating relations

In this paper, we consider estimation of a long-run and a short-run parameter jointly in the presence of nonlinearities. The theory developed establishes limit behavior of minimization estimators of the long- and short-run parameters jointly. Typically, if the long-run parameter that is present in a cointegrating relationship is estimated, its estimator will be superconsistent. Therefore, we may conjecture that the joint minimization estimation of both parameters jointly will result in the same limit distribution for the short-run parameter as if the long-run parameter was known. However, we show that unless a regularity condition holds, this intuition is false in general. This regularity condition, that clearly holds in the standard linear case, is identical to the condition for validity of a two-step Granger–Engle type procedure. Also, it is shown that if the cointegrated variables are measured in deviation from their averages, the standard asymptotic normality result (that one would obtain if the long-run parameter was known) holds.     

Simulation‐based tests of forward‐looking models under VAR learning dynamics

In this paper we propose a simulation‐based technique to investigate the finite sample performance of likelihood ratio (LR) tests for the nonlinear restrictions that arise when a class of forward‐looking (FL) models typically used in monetary policy analysis is evaluated with vector autoregressive (VAR) models. We consider ‘one‐shot’ tests to evaluate the FL model under the rational expectations hypothesis and sequences of tests obtained under the adaptive learning hypothesis. The analysis is based on a comparison between the unrestricted and restricted VAR likelihoods, and the p‐values associated with the LR test statistics are computed by Monte Carlo simulation. We also address the case where the variables of the FL model can be approximated as non‐stationary cointegrated processes. Application to the ‘hybrid’ New Keynesian Phillips Curve (NKPC) in the euro area shows that (i) the forward‐looking component of inflation dynamics is much larger than the backward‐looking component and (ii) the sequence of restrictions implied by the cointegrated NKPC under learning dynamics is not rejected over the monitoring period 1984–2005. Copyright © 2010 John Wiley & Sons, Ltd.     

Trade friction and price discovery in the USD–CAD spot and forward markets

This paper examines the impact of trade friction on price discovery in the USD–CAD spot and forward markets. Using the recently developed fractionally cointegrated vector autoregressive (FCVAR) model, we investigate how the foreign exchange spot and forward markets respond to trade friction. We consider two major trade friction events: the United States–Mexico–Canada Agreement and the recent trade friction between Canada and China. Both events show that the forward market plays a dominant role in price discovery, and the influence of the forward market increases as trade tension increases. By comparing the fractional and non-fractional models, we find that the fractional model fits the data better and has superior forecasting performance to the cointegrated vector autoregressive (CVAR) model.     

An Econometric Analysis of I(2) Variables

This paper provides a selective survey of the recent literature dealing with I(2) variables in economic time series, that is, processes that require to be differenced twice in order to become stationary. With reference to particular economic models intuition is provided of why I(2)-and polynomial cointegration are features likely to occur in economics. The properties of I(2) series are discussed and I review topics such as: Testing for double unit roots, representations of I(2) cointegrated systems, and hypothesis testing in single equations as well as in systems of equations. Different data sets are used to illustrate the various econometric and statistical techniques.     

Adaptive estimation of cointegrated models: simulation evidence and an application to the forward exchange market

The paper reports simulation and empirical evidence on the finite-sample performance of adaptive estimators in cointegrated systems. Adaptive estimators are asymptotically efficient, even when the shape of the likelihood function is unknown. We consider two representations of cointegrated systems—triangular cointegrating regressions and error correction models. The motivation for and advantages of adaptive estimators in such systems are discussed and their construction is described. We report results from the estimation of a forward exchange market unbiasedness regression using the adaptive and competing estimators, and provide related Monte Carlo simulation evidence on the performance of the estimators. Copyright © 1999 John Wiley & Sons, Ltd.     

Forecasting performances of three automated modelling techniques during the economic crisis 2007–2009

In this work we consider the forecasting of macroeconomic variables during an economic crisis. The focus is on a specific class of models, the so-called single hidden-layer feed-forward autoregressive neural network models. What makes these models interesting in the present context is the fact that they form a class of universal approximators and may be expected to work well during exceptional periods such as major economic crises. Neural network models are often difficult to estimate, and we follow the idea of White (2006) of transforming the specification and nonlinear estimation problem into a linear model selection and estimation problem. To this end, we employ three automatic modelling devices. One of them is White’s QuickNet, but we also consider Autometrics, which is well known to time series econometricians, and the Marginal Bridge Estimator, which is better known to statisticians. The performances of these three model selectors are compared by looking at the accuracy of the forecasts of the estimated neural network models. We apply the neural network model and the three modelling techniques to monthly industrial production and unemployment series from the G7 countries and the four Scandinavian ones, and focus on forecasting during the economic crisis 2007–2009. The forecast accuracy is measured using the root mean square forecast error. Hypothesis testing is also used to compare the performances of the different techniques.     

Mixed random forest,cointegration, and forecasting gasoline prices

One of the most successful forecasting machine learning (ML) procedures is random forest (RF). In this paper, we propose a new mixed RF approach for modeling departures from linearity that helps identify (i) explanatory variables with nonlinear impacts, (ii) threshold values, and (iii) the closest parametric approximation. The methodology is applied to weekly forecasts of gasoline prices, cointegrated with international oil prices and exchange rates. Recent specifications for nonlinear error correction (NEC) models include threshold autoregressive models (TAR) and double-threshold smooth transition autoregressive (STAR) models. We propose a new mixed RF model specification strategy and apply it to the determinants of weekly prices of the Spanish gasoline market from 2010 to 2019. In particular, the mixed RF is able to identify nonlinearities in both the error correction term and the rate of change of oil prices. It provides the best weekly gasoline price forecasting performance and supports the logistic error correction model (ECM) approximation.     

NONPARAMETRIC AND SEMIPARAMETRIC PANEL DATA MODELS: RECENT DEVELOPMENTS

In this paper, we provide an intensive review of the recent developments for semiparametric and fully nonparametric panel data models that are linearly separable in the innovation and the individual-specific term. We analyze these developments under two alternative model specifications: fixed and random effects panel data models. More precisely, in the random effects setting, we focus our attention in the analysis of some efficiency issues that have to do with the so-called working independence condition. This assumption is introduced when estimating the asymptotic variance–covariance matrix of nonparametric estimators. In the fixed effects setting, to cope with the so-called incidental parameters problem, we consider two different estimation approaches: profiling techniques and differencing methods. Furthermore, we are also interested in the endogeneity problem and how instrumental variables are used in this context. In addition, for practitioners, we also show different ways of avoiding the so-called curse of dimensionality problem in pure nonparametric models. In this way, semiparametric and additive models appear as a solution when the number of explanatory variables is large.     

Structural equation modeling with ordinal variables: a large sample case study

In the behavioral sciences, response variables are often non-continuous, ordinal variables. Conventional structural equation models (SEMs) have been generalized to accommodate ordinal responses. In this study, three different estimation methods on real data were performed with ordinal variables. Empirical results obtained from the different estimation methods on given real large sample educational data were investigated and compared to recent simulation results. As a result, even very large sample is available, model estimations and fits for ordinal data are affected from inconvenient estimation methods thus it is concluded that asymptotically distribution free estimation method specialized for ordinal variables is more convenient way to model ordinal variables.     

A Unifying Framework for Marginalised Random‐Intercept Models of Correlated Binary Outcomes

We demonstrate that many current approaches for marginal modelling of correlated binary outcomes produce likelihoods that are equivalent to the copula‐based models herein. These general copula models of underlying latent threshold random variables yield likelihood‐based models for marginal fixed effects estimation and interpretation in the analysis of correlated binary data with exchangeable correlation structures. Moreover, we propose a nomenclature and set of model relationships that substantially elucidates the complex area of marginalised random‐intercept models for binary data. A diverse collection of didactic mathematical and numerical examples are given to illustrate concepts. Copyright © 2013 John Wiley & Sons, Ltd.