| ``Cointegration and Aggregation", Review of Economics, (1993) 47, 281-291. Informal Abstract: This paper analyzes the conditions under which cointegration at the micro level implies cointegation at the macro level and vice versa. The latter has not been studied much in the aggregation literature when it is in fact the macro level the one we observe more often. |
|
| ``Five Alternative Methods of Estimating Long Run Equilibrium Relationships", Journal of Econometrics (1994), 60, 1-31. Informal Abstract: This is the first paper to study the asymptotic distribution of principal components and canonical correlation methods (between Xt and Xt-1) to estimate the cointegrating vector. These methods are compared theoretically with OLS, NLS and ML. The paper concludes with a simulation exercise comparing the finite sample performance of these five methods to conclude that in the IQR metric ML is superior to the other ones. To show how relevant is the estimation method in practice, the paper starts with an application of the term structure of the interest rates showing that the cointegrating vector varies depending on the method used. |
|
``Estimation of Common Long Memory Components in Cointegrated Systems" (with C. Granger), Journal of Business & Economic Statistics (1995), 13, 27-36. Informal Abstract: This papers proposes a simple way of finding why a set of variables is cointegrated. As a by-product proposes a new Permanent and Transitory multivariate decomposition. |
|
| ``No Lack of Relative Power of the DF Type Tests" (with T.Lee), Journal of Time Series Analysis (1996), 17, 37-47. Informal Abstract: All the tests have a lack of power in finite samples. This paper shows that the power of the DF test for testing rho=1 versus rho<1 is NOT smaller than the power the Wald test for testing rho=.5 versus rho<.5. Of course the consequences are different; but this is a different issue. |
|
| ``P-values of Non-Standard Distributions: The DF Case" (with J. Adda), Economic Letters (1996), 50, 155-160. Informal Abstract: |
|
``Testing for Multicointegration" (with Tom Engsted and Niels Haldrup), Economics Letters (1997), 56, 259-266. Informal Abstract: |
|
``On the Exact Moments of Non-Standard Asymptotic Distributions in Non-Stationary Autoregressions with Dependent Errors'' (with J-Y Pitarakis), International Economic Review (1998), 39, 71-88. Informal Abstract: |
|
| "Pitfalls in Testing for Long Run relationships" (con Tae Lee), Journal of Econometrics (1998), 86, 129-154. In the Most Requested Articles of the JEC (unto and including Nov'99). Informal Abstract: |
|
| ``Specification via Model Selection in Vector Error Correction Models" (with J-Y Pitarakis), Economics Letters (1998), 60, 321-328. Informal Abstract: |
|
| ``Dimensionality Effect in Cointegration Analysis" (with J-Y Pitarakis), Festschrift in Honour of Clive Granger, edited by R. Engle and H. White (1999), 212-229.Oxford University Press. Informal Abstract: |
|
| "A Systematic Framework for Analyzing the Dynamic Effects of Permanent and Transitory Shocks" (with Serena Ng), Journal of Economic Dynamics & Control, (2001), 25, 1527-1546. Informal Abstract: |
|
| "A Primer in Cointegration" (with Juan Jose Dolado and Francesc Marmol), chapter 30 in Baltagui, A Companion to Theoretical Econometrics, 2001, edited by B.H. Baltagui, Blackwell, New York. Informal Abstract: |
|
| "On the Robutness of Cointegration Tests when Series are Fractionally Integrated" (with Tae Lee), Journal of Applied Statistics (2000),vol 27, No 7, 821-827. Informal Abstract: |
|
"Lag Lenth Estimation in Large Dimensional Systems" (with Jean-Yves Pitarakis), Journal of Time Series Analysis (2002), Vol 23, No. 4, 401-423. Informal Abstract: |
|
"Estimation and Model Selection Based Inference in Single and Multiple Threshold Models" (with Jean-Yves Pitarakis), Journal of Econometrics (2002), 110, 319-352. Informal Abstract: |
|
| "A Fractional Dickey-Fuller Test" (with Juan Jose Dolado and Laura Mayoral), Econometrica (2002), vol 70, No5, 1963-2006. Informal Abstract: |
|
| "Long Memory in the Spanish Political Opinion Polls" (with Juan J. Dolado and Laura Mayoral), Journal of Applied Econometrics (2003), vol 18, No. 2, 137-155. Informal Abstract: |
|
| "Which Extreme
Values Are
Really Extremes?" (with Jose Olmo), Journal of Financial
Econometrics (2004), Vol 2, No 3, 349-369. Informal Abstract: |
|
"Subsampling Inference in Threshold Autoregressive Models" (with Michael Wolf), Journal of Econometrics (2005), 127, 201-224. Informal Abstract: |
|
| "Threshold Effects
in Multivariate
Error Correction Models" (with Jean-Yves Pitarakis), Palgrave Handbook of
Econometrics, 2006, Vol I, Chapter 15. Informal Abstract: |
|
"Large versus small Shocks (or Does Size Matter? Maybe so)" (with Oscar Martinez), Journal of Econometrics (2006), 135, 311-347. Informal Abstract: |
|
| "Threshold Effects in
Cointegrating Regressions" (with Jean-Yves
Pitarakis), Oxford
Bulletin of Economics and Statistics (2006), 813-833. Informal Abstract: |
|
"Permanent and Transitory Components of GDP and Stock Prices: Further Analysis" (with Tae-Hwy Lee and Weiping Yang), Macroeconomics and Finance in Emerging Market Economies, (2008), Vol 1, 105-120. Informal Abstract: |
|
"WALD Tests of I(1) Against I(d) Alternatives: Some New Properties and Extension to Processes with Trending Components" (with Juan J. Dolado and Laura Mayoral). Studies in Nonlinear Dynamics and Econometrics, (2008), vol 12, Article 1 (pages 1-32). Informal Abstract: |
|
| "Simple
WALD
Tests of the Fractional Integration Parameter: An Overview of New
Results" (with
Juan J. Dolado and Laura
Mayoral), in The Methodology and
Practice of Econometrics, edited by J. Castle and N. Shephard, .Oxford University Press
(2009), pages 300-321. Informal Abstract: |
|
| "Modelling and Measuring Price Discovery
in
Commodity Markets" (with
Isabel Figuerola-Ferreti), Journal of Econometrics 158 (2010), 95-107. Informal Abstract: |
|
“The Making of Estimation of Common Long Memory Components in Cointegrated Systems”, Journal of Financial Econometrics (2010), Vol 8, No. 2, 174-176. | |
"Regime Specific Predictability in Predictive Regressions" (with Jean-Yves Pitarakis), Journal of Business and Economic Statistics, vol 30, issue 2, 2012, pages 229-241. Informal Abstract: Predictive regressions are linear specifications linking a noisy variable such as stock returns to past values of a very persistent regressor with the aim of assessing the presence of predictability. Key complications that arise are the potential presence of endogeneity and the poor adequacy of asymptotic approximations. In this article, we develop tests for uncovering the presence of predictability in such models when the strength or direction of predictability may alternate across different economically meaningful episodes. An empirical application reconsiders the dividend yield-based return predictability and documents a strong predictability that is countercyclical, occurring solely during bad economic times. This article has online supplementary materials. | |
| "Estimation and Inference in Threshold Type Regime Switching Models" (with
Jean-Yves Pitarakis), Chapter 8th in Handbook of Research Methods andApplications in Empirical Macroeconomics (EE Handbook), pages 189-205. (forthcoming 2013) | |
| "Summability of Stochastic Processes (A Generalization of Integration and Co-integration valid for Non-linear Processes)" (with
Vanessa Berenguer-Rico), Journal
of Econometrics 178 (2014) 331–341. [The degree of Summability can be easily estimated in E-Views] The code used for this paper: SummabilityMatlab , SummabilityGauss A Short Informal Abstract: The order of integration is valid to characterize linear processes; but it is not appropriate for non-linear worlds. We propose the concept of summability (a re-scaled partial sum of the process being Op(1)) to handle non-linearities. The paper shows that this new concept, S (delta): (i) generalizes I (delta); (ii) measures the degree of persistence as well as of the evolution of the variance; (iii) controls the balancedness of non-linear relationships; (iv) opens the door to the concept of co-summability which represents a generalization of co-integration for non-linear processes. To make this concept empirically applicable, an estimator for delta and its asymptotic properties are provided. The …nite sample performance of subsampling con…dence intervals is analyzed via a Monte Carlo experiment. The paper …finishes with the estimation of the degree of summability of the macroeconomic variables in an extended version of the Nelson-Plosser database. |
|
| "Conditional Stochastic Dominance Tests in Dynamic Settings" (with
Jose Olmo), International Economic Review 55 (2014), 3, 819-838. A Short Informal Abstract: This paper proposes nonparametric consistent tests of conditional stochastic dominance of arbitrary order in a dynamic setting. The novelty of these tests lies in the nonparametric manner of incorporating the information set into the test. The test allows for general forms of unknown serial and mutual dependence between random variables, and has an asymptotic distribution that can be easily approximated by simulation. This method has good finite-sample performance. These tests are applied to determine the investment efficiency between US industry portfolios conditional on the dynamics of the market portfolio. The empirical analysis suggests that Telecommunications dominates the other sectoral portfolios under risk aversion. |
|
|
"Detecting Big Structural Breaks in Large Factor Model" (with
Liang Cheng and Juan Jose Dolado) (PDF + Online Appendix), Journal
of Econometrics 180 (May 2014), Issue 1, Pages 30–48.
[It is amazing how easily can this test be implemented in
E-Views....A huge advantage with respect other existing tests]
A Short Informal Abstract: Time invariance of factor loadings is a standard assumption in the analysis of large factor models. Yet, this assumption may be restrictive unless parameter shifts are mild (i.e., local to zero). In this paper we develop a new testing procedure to detect big breaks in these loadings at either known or unknown dates. It relies upon testing for parameter breaks in a regression of one of the factors estimated by Principal Components analysis on the remaining estimated factors, where the number of factors is chosen according to Bai and Ng’s (2002) information criteria. The test fares well in terms of power relative to other recently proposed tests on this issue, and can be easily implemented to avoid forecasting failures in standard factor-augmented (FAR, FAVAR) models where the number of factors is a priori imposed on the basis of theoretical considerations. |
|
| "Inferring the Predictability Induced by a Persistent Regressor in a Predictive Threshold Model" (with
Jean-Yves Pitarakis) (PDF) + (Appendix), Journal of Business and Economic
Statistics, Volume 35, 2017, Pages 202-217. A Short Informal Abstract: In this paper we develop a distributional theory for detecting predictability induced by a per- sistent variable. Our framework is that of a predictive regression model with threshold e ects and our goal is to develop operational and easily implementable inferences when one does not want to impose a priori restrictions on the parameters other than the slopes corresponding to the persistent predictor. Diferently put our tests for the null hypothesis of no predictability against threshold style predictbility across two regimes remain valid without the need to know whether the remaining pa- rameters of the model are characterised by threshold efects or not (e.g. shifting versus non-shifting intercepts). One interesting feature of our setting is that our test statistic remains unafected by whether some nuisance parameters are identified or not.
|
|
"Differences between short and long term risk aversion: an optimal asset allocations perspective" (with Jose Olmo) (PDF ) (Appendix Online). OXFORD BULLETIN OF ECONOMICS AND STATISTICS, 81, 1 (2019) pages 42-61. A Short Informal Abstract: This paper studies the long-term asset allocation problem of an investor with di er-
ent risk aversion attitudes to the short and the long term. To do this, we characterize investor's preferences with a utility function exhibiting a regime shift in risk aversion at some point of the multiperiod investment horizon. In this framework, the optimal asset allocation is determined by a parametric linear portfolio policy rule driven by a set of state variables. The parameters determining the optimal portfolio weights are estimated and tested using GMM. The presence of di erent regimes in risk aversion is tested using threshold nonlinearity likelihood ratio tests. Our empirical results for a portfolio of cash, bonds and stocks provide statistical evidence of di erences in risk aversion between the short-term and the long-term estimated around the seventh month of the investment hori- zon. Long-term risk aversion is always higher than short-term risk aversion and increases with the investment horizon. The allocation to stocks and bonds is strongly negatively correlated and increases with the investment horizon |
|
| "Trends in Distributional Characteristics: Existence of Global Warming" (with Lola Gadea) (PDF). Journal of Econometrics (forthcoming 2018) A Short Informal Abstract: What type of global warming exists? This study introduces a novel methodology to answer this question, which is the starting point for all issues related to climate change analyses. Global warming is defined as an increasing trend in certain distributional characteristics (moments, quantiles, etc.) of global temperatures, in addition to simply examining the average values. Temperatures are viewed as a functional stochastic process from which we obtain distributional characteristics as time series objects. Here, we present a simple robust trend test and prove that it is able to detect the existence of an unknown trend component (deterministic or stochastic) in these characteristics. Applying this trend test to daily temperatures in Central England (for the period 1772{2017) and to global cross-sectional temperatures (1880{2015), we obtain the same strong conclusions: (i) there is an increasing trend in all distributional characteristics (time series and cross-sectional), and this trend is larger in the lower quantiles than it is in the mean, median, and upper quantiles; (ii) there is a negative trend in the characteristics that measure dispersion (i.e., lower temperatures approach the median faster than higher temperatures do). This type of global warming has more serious consequences than those found by analyzing only the average. |
|
WORKING PAPERS |
|