Time Variation Of Coefficients Research Articles

Predicting future inflation in Indonesia using Dynamic Model Averaging (DMA)

The features of Indonesia's inflation data, which make it extremely susceptible to shocks like those felt in 2005 and 2008, as well as extensive potential influencing factors, lead to problems in forecasting inflation. These problems include time variation in coefficients, models that can change over time, and many predictors to consider. Dynamic Model Averaging (DMA) solves these problems since it has evolved coefficients and models that change over time. This study uses DMA to predict future inflation by involving eight macroeconomic indicators as exogenous variables. The results of the in-sample analysis show that six predictors are significant in forecasting inflation, with posterior inclusion probability (PIP) being above 40%. Although the remaining predictors have PIP means below 40%, they can still be considered important. The out-of-sample results suggest that DMA performs better than dynamic model selection and models that don’t include exogenous variables, such as autoregressive models. The forecast results indicate a consistent pattern over the 12 months studied. The attempt to control inflation can be achieved by prioritizing the money supply factor, which has the highest PIP value, indicating that it is the most important factor.

Vascular and metabolic risk factor differences prior to dementia diagnosis: a multidatabase case–control study using European electronic health records

ObjectiveThe objective of the study is to compare body mass index (BMI), systolic/diastolic blood pressure (SBP/DBP) and serum total cholesterol levels between dementia cases and controls at multiple time intervals...

Forecasting Volatility with Time-Varying Coefficient Regressions

We extend the heterogeneous autoregressive- (HAR-) type models by explicitly considering the time variation of coefficients in a Bayesian framework and comprehensively comparing the performances of these time-varying coefficient models and constant coefficient models in forecasting the volatility of the Shanghai Stock Exchange Composite Index (SSEC). The empirical results suggest that time-varying coefficient models do generate more accurate out-of-sample forecasts than the corresponding constant coefficient models. By capturing and studying the time series of time-varying coefficients of the predictors, we find that the coefficients (predictive ability) of heterogeneous volatilities are negatively correlated and the leverage effect is not significant or inverse during certain periods. Portfolio exercises also demonstrate the superiority of time-varying coefficient models.

Time-varying skills (versus luck) in U.S. active mutual funds and hedge funds

Abstract In this paper, we develop a nonparametric methodology for estimating and testing time-varying fund alphas and betas as well as their long-run counterparts (i.e., their time-series averages). Traditional linear factor model arises as a special case without time variation in coefficients. Monte Carlo simulation evidence suggests that our methodology performs well in finite samples. Applying our methodology to U.S. mutual funds and hedge funds, we find most fund alphas decrease with time. Combining our methodology with the bootstrap method which controls for ‘luck’, positive long-run alphas of mutual funds but hedge funds disappear, while negative long-run alphas of both mutual and hedge funds remain. We further check the robustness of our results by altering benchmarks, fund skill indicators and samples.

ON THE SOURCES OF UNCERTAINTY IN EXCHANGE RATE PREDICTABILITY

AbstractIn a unified framework, we examine four sources of uncertainty in exchange rate forecasting models: (i) random variations in the data, (ii) estimation uncertainty, (iii) uncertainty about the degree of time variation in coefficients, and (iv) uncertainty regarding the choice of the predictor. We find that models that embed a high degree of coefficient variability yield forecast improvements at horizons beyond one month. At the one‐month horizon, and apart from the standard variance implied by unpredictable fluctuations in the data, the second and third sources of uncertainty listed above are key obstructions to predictive ability. The uncertainty regarding the choice of the predictors is negligible.

Stock Return Prediction with Fully Flexible Models and Coefficients

We evaluate stock return predictability using a fully flexible Bayesian framework, which explicitly allows for different degrees of time-variation in coefficients and in forecasting models. We believe that asset return predictability can evolve quickly or slowly, based upon market conditions, and we should account for this. Our approach has superior out-of-sample predictive performance compared to the historical mean, from a statistical and economic perspective. We also find that our model statistically dominates its nested models, including models in which parameters evolve at a constant rate. By decomposing sources of prediction uncertainty into five parts, we find that our fully flexible approach more precisely identifies time-variation in coefficients and in forecasting models, leading to mitigation of estimation risk and forecasting improvements. Finally, we relate predictability to the business cycle.

Specification tests for time-varying parameter models with stochastic volatility

ABSTRACTWe propose an easy technique to test for time-variation in coefficients and volatilities. Specifically, by using a noncentered parameterization for state space models, we develop a method to directly calculate the relevant Bayes factor using the Savage–Dickey density ratio—thus avoiding the computation of the marginal likelihood altogether. The proposed methodology is illustrated via two empirical applications. In the first application, we test for time-variation in the volatility of inflation in the G7 countries. The second application investigates if there is substantial time-variation in the nonaccelerating inflation rate of unemployment (NAIRU) in the United States.

Stock Return Prediction with Fully Flexible Models and Coefficients

We evaluate stock return predictability using a fully flexible Bayesian framework, which explicitly allows for different degrees of time-variation in coefficients and in forecasting models. We believe that asset return predictability can evolve quickly or slowly, based upon market conditions, and we should account for this. Our approach has superior out-of-sample predictive performance compared to the historical mean, from a statistical and economic perspective. We also find that our model statistically dominates its nested models, including models in which parameters evolve at a constant rate. By decomposing sources of prediction uncertainty into five parts, we find that our fully flexible approach more precisely identifies time-variation in coefficients and in forecasting models, leading to mitigation of estimation risk and forecasting improvements. Finally, we relate predictability to the business cycle.

Specification Tests for Time-Varying Parameter Models with Stochastic Volatility

We propose an easy technique to test for time-variation in coefficients and volatilities. Specifically, by using a noncentered parameterization for state space models, we develop a method to directly calculate the relevant Bayes factor using the Savage-Dickey density ratio — thus avoiding the computation of the marginal likelihood altogether. The proposed methodology is illustrated via two empirical applications. In the first application we test for time-variation in the volatility of inflation in the G7 countries. The second application investigates if there is substantial time-variation in the NAIRU in the US.

On the Sources of Uncertainty in Exchange Rate Predictability

In a unified framework, we examine four sources of uncertainty in exchange rate forecasting models: (i) random variations in the data, (ii) estimation uncertainty, (iii) uncertainty about the degree of time-variation in coefficients, and (iv) uncertainty regarding the choice of the predictor. We find that models which embed a high-degree of coefficient variability yield forecast improvements at horizons beyond 1-month. At the 1-month horizon, and apart from the standard variance implied by unpredictable fluctuations in the data, the second and third sources of uncertainty listed above are key obstructions to predictive ability. The uncertainty regarding the choice of the predictors is negligible.

Forecasting UK GDP Growth, Inflation and Interest Rates under Structural Change: A Comparison of Models with Time-Varying Parameters

Evidence from a large and growing empirical literature strongly suggests that there have been changes in inflation and output dynamics in the United Kingdom. This is largely based on a class of econometric models that allow for time-variation in coefficients and volatilities of shocks. While these have been used extensively to study evolving dynamics and for structural analysis, there is little evidence on their usefulness in forecasting UK output growth, inflation and the short-term interest rate. This paper attempts to fill this gap by comparing the performance of a wide variety of time-varying parameter models in forecasting output growth, inflation and a short rate. We find that allowing for time-varying parameters can lead to large and statistically significant gains in forecast accuracy.

Predictive regressions with time-varying coefficients

We evaluate predictive regressions that explicitly consider the time-variation of coefficients in a comprehensive Bayesian framework. For monthly returns of the S&P 500 index, we demonstrate statistical as well as economic evidence of out-of-sample predictability: relative to an investor using the historic mean, an investor using our methodology could have earned consistently positive utility gains (between 1.8% and 5.8% per year over different time periods). We also find that predictive models with constant coefficients are dominated by models with time-varying coefficients. Finally, we show a strong link between out-of-sample predictability and the business cycle.

Predictive Regressions with Time-Varying Coefficients

We evaluate predictive regressions that explicitly consider the time-variation of coefficients in a comprehensive Bayesian framework. This allows for fast and consistent adjustment of regression coefficients to changes in the underlying economic relationships. For monthly returns of the S&P 500 index, we demonstrate statistical as well as economic evidence of out-of-sample predictability: relative to an investor using the historic mean an investor using our methodology could have earned consistently positive utility gains (between 1.8 and 5.8% p.a. over different time periods). Furthermore, we show that predictive models with constant coefficients are dominated by models with time-varying coefficients.

Equity Return Prediction: Are Coefficients Time-Varying?

Most papers in equity return prediction rely on the assumption that coefficients in linear predictive models are constant over time. We question and relax this assumption and find strong empirical support for the validity of models allowing for time varying regression coefficients. Analyzing model uncertainty, we document that uncertainty about the level of time-variation in coefficients and uncertainty about the choice of predictive variables are equally important sources of predictive variance. Furthermore, we document out-of-sample predictability of the average and individual predictive models. Most importantly, only individual predictive models with time-varying coefficients show out-of-sample predictability across all periods of time.