Time-varying Coefficient Models Research Articles

Portfolio Optimization for Hedge Funds Through Time-Varying Coefficients

In this paper, we show the interest of the time-varying coefficient model in hedge fund performance assessment and selection. We argue that the alpha of hedge funds is dynamic and that the time-varying alpha captures this dynamic behavior. Therefore, forming portfolios based on their time-varying alpha should lead to outperforming portfolios. Using a persistence analysis, we check this conjecture and show that contrary to top performers in terms of OLS alpha, the top performers in terms of past time-varying alpha generate superior and significant ex-post performance. Additionally, this analysis shows that persistence exists in the hedge fund industry and can be as long as 3 years. Secondly, building on the conclusion that the time-varying analysis gives a better picture of the alpha of the manager at a certain point in time, we use the time-varying analysis to obtain estimates of the expected returns of hedge funds. Using those estimates to construct a mean-variance optimal portfolio enhances the performance of this portfolio, suggesting that in terms of hedge fund performance detection, the time-varying model is superior to the OLS analysis.

La demande de monnaie dans la zone euro revisitée

Résumé L’article propose une analyse empirique de la demande de monnaie (M3) dans la zone euro sur la période 1981-2008. Pour expliquer la croissance rapide de l’agrégat M3 depuis 2001, des variables de richesse relatives aux prix des actifs financiers et immobiliers en termes réels sont introduites. Deux méthodes d’estimation sont utilisées : un modèle vectoriel à correction d’erreurs et un modèle à coefficients variables. La première approche montre qu’en incluant les variables de richesse dans le modèle, nous obtenons un modèle apparemment stable sur la période 1981-2007, mais l’extension de la période d’estimation affecte sa stabilité et remet en question sa pertinence. La seconde approche révèle l’instabilité des fonctions de demande de monnaie – les élasticités et semi-élasticités varient au cours du temps – et met en évidence une relation positive entre les prix des actifs immobiliers et la demande de monnaie (M3) en termes réels. La richesse immobilière joue par conséquent un rôle important pour capturer les comportements d’allocation de portefeuille dans les modèles de demande de monnaie durant la première décennie de ce siècle.

Statistical inference for partially time-varying coefficient errors-in-variables models

This paper studies the partially time-varying coefficient models where some covariates are measured with additive errors. In order to overcome the bias of the usual profile least squares estimation when measurement errors are ignored, we propose a modified profile least squares estimator of the regression parameter and construct estimators of the nonlinear coefficient function and error variance. The proposed three estimators are proved to be asymptotically normal under mild conditions. In addition, we introduce the profile likelihood ratio test and then demonstrate that it follows an asymptotically χ2 distribution under the null hypothesis. Finite sample behavior of the estimators is investigated via simulations too.

FORECASTING INFLATION USING DYNAMIC MODEL AVERAGING*

We forecast quarterly US inflation based on the generalized Phillips curve using econometric methods that incorporate dynamic model averaging. These methods not only allow for coefficients to change over time, but also allow for the entire forecasting model to change over time. We find that dynamic model averaging leads to substantial forecasting improvements over simple benchmark regressions and more sophisticated approaches such as those using time varying coefficient models. We also provide evidence on which sets of predictors are relevant for forecasting in each period.

Inference of time-varying regression models

We consider parameter estimation, hypothesis testing and variable selection for partially time-varying coefficient models. Our asymptotic theory has the useful feature that it can allow dependent, nonstationary error and covariate processes. With a two-stage method, the parametric component can be estimated with a $n^{1/2}$-convergence rate. A simulation-assisted hypothesis testing procedure is proposed for testing significance and parameter constancy. We further propose an information criterion that can consistently select the true set of significant predictors. Our method is applied to autoregressive models with time-varying coefficients. Simulation results and a real data application are provided.

Empirical likelihood for partially time-varying coefficient models with dependent observations

In this paper, we apply the empirical likelihood method to study the partially time-varying coefficient models with a random design and a fixed design under dependent assumptions. A nonparametric version of Wilks’ theorem is derived for the fixed-design case. For the random-design case, it is proved that the empirical log-likelihood ratio of the regression parameters admits a limiting distribution with a weighted sum of independent chi-squared distributions. In order that Wilks’ phenomenon holds, we propose an adjusted empirical log-likelihood (ADEL) ratio for the regression parameters. The ADEL is shown to have a standard chi-squared limiting distribution. Simulation studies are undertaken to indicate that the proposed methods work better than the normal approximation-based approach.

Bayesian Analysis of Coefficient Instability in Dynamic Regressions

This paper proposes a Bayesian regression model with time-varying coefficients (TVC) that makes it possible to estimate jointly the degree of instability and the time-path of regression coefficients. Thanks to its computational tractability, the model proves suitable to perform the first (to our knowledge) Monte Carlo study of the finite-sample properties of a TVC model. Under several specifications of the data generating process, the proposed model’s estimation precision and forecasting accuracy compare favourably with those of other methods commonly used to deal with parameter instability. Furthermore, the TVC model leads to small losses of efficiency under the null of stability and it is robust to mis-specification, providing a satisfactory performance also when regression coefficients experience discrete structural breaks. As a demonstrative application, we use our TVC model to estimate the exposures of S&P 500 stocks to market-wide risk factors: we find that a vast majority of stocks have time-varying risk exposures and that the TVC model helps to forecast these exposures more accurately.

Research on the Dynamic Relationship between Prices of Agricultural Futures in China and Japan

Based on the classical regression model, time-varying coefficient model, unit root, co-integration, Granger causality test, VAR, impulse response and variance decomposition, the dynamic relationship between prices of natural rubber futures in China and Japan has been researched systematically. The following conclusions are gotten through empirical researches: Firstly, there is a stable co-integration relationship between prices of natural rubber futures in China and Japan. Secondly, the time-varying coefficient model is superior to the classical regression model. The influence of price of natural rubber futures in Japan on price of natural rubber futures in China is time-varying. In the long run, the impact of natural rubber futures in Japan on natural rubber futures in China has been gradually increased. Thirdly, the influence of price of natural rubber futures in Japan on price in China is greater than the influence of price in China on price in Japan.

Estimación de las Componentes de un Modelo de Coeficientes Dinámicos Mediante las Ecuaciones de Estimación Generalizadas (Time-Varying Coefficient Model Component Estimation Through Generalized Estimation Equations)

ResumenSe propone una metodologia para estimar las componentes de un modelode coeficientes dinamicos mediante las ecuaciones de estimacion generaliza-das (Liang & Zeger 1986), con el proposito de incluir directamente en laestimacion la posible correlacion de las medidas repetidas de cada individuo.La expansion de los coeficientes dinamicos del modelo se lleva a cabo a tra-ves de regresion spline (Huang et al. 2002). Tambien se propone utilizar elcriterio de informacion de Akaike en las ecuaciones de estimacion generali-zadas (QIC) (Pan 2001) como selector de modelos. Mediante simulacion secompara la metodologia propuesta con la metodologia presentada por Wu &Zhang (2006), donde se estiman las componentes del modelo mediante mini-mos cuadrados ponderados y se utiliza el criterio de informacion de Akaike(AIC) como selector de modelos, obteniendose que en los escenarios simu-lados la metodologia propuesta presenta mejores resultados con relacion alerror cuadratico medio promedio. Para ilustrar la estrategia de estimacionpropuesta, se considera el conjunto de datos ACTG 315 (Liang et al. 2003)asociado con un estudio de sida, en el que se modela dinamicamente la rela-cion entre la carga viral y el conteo de celulas CD4+.Palabras clave: criterio de informacion de Akaike, ecuaciones de estima-cion generalizadas, minimos cuadrados ponderados, modelo de coeficientesdinamicos, regresion spline.Abstract

Sovereign bond yield spreads: A time-varying coefficient approach

We study the determinants of sovereign bond yield spreads across 10 EMU countries between Q1/1999 and Q1/2010. We apply a semiparametric time-varying coefficient model to identify, to what extent an observed change in the yield spread is due to a shift in macroeconomic fundamentals or due to altering risk pricing. We find that at the beginning of EMU, the government debt level and the general investors’ risk aversion had a significant impact on interest differentials. In the subsequent years, however, financial markets paid less attention to the fiscal position of a country and the safe haven status of Germany diminished in importance. By the end of 2006, two years before the fall of Lehman Brothers, financial markets began to grant Germany safe haven status again. One year later, when financial turmoil began, the market reaction to fiscal loosening increased considerably. The altering in risk pricing over time period confirms the need of time-varying coefficient models in this context.

Sovereign Bond Yield Spreads: A Time-Varying Coefficient Approach

We study the determinants of sovereign bond yield spreads across 10 EMU countries between Q1/1999 and Q1/2010. We apply a semiparametric time-varying coefficient model to identify, to what extent an observed change in the yield spread is due to a shift in macroeconomic fundamentals or due to altering risk pricing. We find that at the beginning of EMU, the government debt level and the general investors' risk aversion had a significant impact on interest differentials. In the subsequent years, however, financial markets paid less attention to the fiscal position of a country and the safe haven status of Germany diminished in importance. By the end of 2006, two years before the fall of Lehman Brothers, financial markets began to grant Germany safe haven status again. One year later, when financial turmoil began, the market reaction to fiscal loosening increased considerably. The altering in risk pricing over time period confirms the need of time-varying coefficient models in this context.

A space–time varying coefficient model: The equity of service accessibility

Research in examining the equity of service accessibility has emerged as economic and social equity advocates recognized that where people live influences their opportunities for economic development, access to quality health care and political participation. In this research paper service accessibility equity is concerned with where and when services have been and are accessed by different groups of people, identified by location or underlying socioeconomic variables. Using new statistical methods for modeling spatial-temporal data, this paper estimates demographic association patterns to financial service accessibility varying over a large geographic area (Georgia) and over a period of 13 years. The underlying model is a space--time varying coefficient model including both separable space and time varying coefficients and space--time interaction terms. The model is extended to a multilevel response where the varying coefficients account for both the within- and between-variability. We introduce an inference procedure for assessing the shape of the varying regression coefficients using confidence bands.

Measurement of causal effects

Three types of stochastic coefficient models can be identified: models with “individually-varying”, “time-varying” and “individually- and time-varying” coefficients. A parameterized stochastic coefficient environment is well suited to measure the causal effects of the explanatory variables on the dependent variable of a law. This environment captures the unknown true functional form of the law as a special case. In the presence of omitted variables and measurement errors, each coefficient of the law stated in terms of only included variables is the sum of the bias-free term and omitted variables bias with or without measurement-error bias. A method of separating the bias-free term from these biases is developed. This method is shown to be different from the instrumental variables method by showing that the instrumental variables do not exist. Laws are also shown to be different from regression models. Models having lagged dependent variables and the current and lagged values of explanatory variables as its regressors are used for policy analysis and testing for Granger causality in the econometric literature. These models are shown to be non-parsimonious relative to certain types of time-varying coefficient models without lagged dependent variables and are shown to lead to identification problems.

Statistical inference in partially time-varying coefficient models

A partially time-varying coefficient time series model is introduced to characterize the nonlinearity and trending phenomenon. To estimate the regression parameter and the nonlinear coefficient function, the profile least squares approach is applied with the help of local linear approximation. The asymptotic distributions of the proposed estimators are established under mild conditions. Meanwhile, the generalized likelihood ratio test is studied and the test statistics are demonstrated to follow asymptotic χ 2 -distribution under the null hypothesis. Furthermore, some extensions of the proposed model are discussed and several numerical examples are provided to illustrate the finite sample behavior of the proposed methods.

Effect of changes in season and temperature on mortality associated with air pollution in Seoul, Korea

BackgroundsGlobal warming has increased concern about the synergistic or interactive effects of temperature and air pollution on human health. The aim of this study was to examine the effect of...

Time-varying linkages between tourism receipts and economic growth in a small open economy

The causal link between tourism receipts and GDP has recently become the major focus of some recent studies in tourism economics. Results obtained in these studies about the causal link appear to be sensitive with respect to the countries analyzed, sample period and methodology employed. Considering the sensitivity of the causal link, we use the rolling window and time-varying coefficients estimation methods to analyze the Granger causality based on Vector Error Correction Model (VECM). When applied to Turkey for the 1963–2006 periods, this methodology enables us to overcome differences in the outcome of the tests performed in other studies for tourism receipts and GDP. The findings of this paper are as follows: results from the full sample within the VECM model indicate that there is no Granger causality between the series, while the findings from the time-varying coefficients model based on the state-space model and rolling window technique show that GDP has no predictive power for tourism receipts; however, tourism receipts have a positive–predictive content for GDP following early 1980s.

Uncovering Symptom Progression History from Disease Registry Data with Application to Young Cystic Fibrosis Patients

The growing availability of various disease registry data has brought precious opportunities to epidemiologists to understand the natural history of the registered diseases. It also presents challenges to the traditional data analysis techniques because of complicated censoring/truncation schemes and temporal dynamics of covariate influences. In a case study of the Cystic Fibrosis Foundation Patient Registry data, we propose analyses of progressive symptoms using temporal process regressions, as an alternative to the commonly employed proportional hazards models. Two endpoints are considered, the prevalence of ever positive and currently positive for Pseudomonas aeruginosa (PA) infection in the lungs, which capture different aspect of the disease process. The analysis of ever PA positive via a time-varying coefficient model demonstrates the lack of fit, as well as the potential loss of information, in the standard proportional hazards analysis. The analysis of currently PA positive yields results that are clinically meaningful and have not previously been reported in the cystic fibrosis literature. Our analyses demonstrate that prenatal/neonatal screening results in lower prevalence of PA infection compared to traditional diagnosis via signs and symptoms, but this benefit attenuates with age. Calendar years of diagnosis also affect the risk of PA infection; patients diagnosed in more recent cohort show higher prevalence of ever PA positive but lower prevalence of currently PA positive.

Sales Growth of New Pharmaceuticals Across the Globe: The Role of Regulatory Regimes

Prior marketing literature has overlooked the role of regulatory regimes in explaining international sales growth of new products. This paper addresses this gap in the context of new pharmaceuticals (15 new molecules in 34 countries) and sheds light on the effects of regulatory regimes on new drug sales across the globe. Based on a time-varying coefficient model, we find that differences in regulation substantially contribute to cross-country variation in sales. One of the regulatory constraints investigated, i.e., manufacturer price controls, has a positive effect on drug sales. The other forms of regulation such as restrictions of physician prescription budgets and the prohibition of direct-to-consumer advertising (DTCA) tend to hurt sales. The effect of manufacturer price controls is similar for newly launched and mature drugs. By contrast, regulations on physician prescription budgets and DTCA have a differential effect for newly launched and mature drugs. Whereas the former hurts mature drugs more, the latter has a larger effect on newly launched drugs. In addition to these regulatory effects, we find that national culture, economic wealth, and lagged sales also affect drug sales. Our findings may be used as input by managers for international launch and marketing decisions. They may also be used by public policy administrators to assess the role of regulatory regimes in pharmaceutical sales growth.

Variable selection in partially time-varying coefficient models

A partially time-varying coefficient model is introduced to characterise the nonlinearity and trending phenomenon. To enhance predictability and to select significant variables in the parametric component of the model, the penalised least squares method with the help of the profile local linear technique is developed in this article. The convergence rate and the oracle property of the resulting estimator are established under mild conditions. A remarkable achievement of our results is that it does not require undersmoothing of the nonparametric component. Meanwhile, some extensions of the proposed model and method are also discussed. Furthermore, some numerical examples are provided to show that our theory and method work well in practice.

Forecasting Inflation Using Dynamic Model Averaging

We forecast quarterly US inflation based on the generalized Phillips curve using econometric methods which incorporate dynamic model averaging. These methods not only allow for coefficients to change over time, but also allow for the entire forecasting model to change over time. We find that dynamic model averaging leads to substantial forecasting improvements over simple benchmark regressions and more sophisticated approaches such as those using time varying coefficient models. We also provide evidence on which sets of predictors are relevant for forecasting in each period.