Éric Ghysels
Biographic Data
| ID | 5851557 |
|---|---|
| NAME | Éric Ghysels |
| GIVEN NAMES | Éric |
| FAMILY NAME | Ghysels |
| SIGNATURE | GHYSELS E |
| AFFILIATIONS | University of North Carolina at Chapel Hill |
| ORCID | 0000-0002-7125-2040 |
| VERIFIED | Yes |
| TOTAL WORKS | 24 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 24 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 1987 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 0 |
Panel data nowcasting
The paper uses structured machine learning regressions for nowcasting with panel data consisting of series sampled at different frequencies. Motivated by the problem of predicting corporate earnings for a large cross‐section of firms with macroeconomic, financial, and news time series sampled at different frequencies, we focus on the sparse‐group LASSO regularization which can take advantage of the mixed‐frequency time series panel data structure…
Machine Learning Time Series Regressions With an Application to Nowcasting
This article introduces structured machine learning regressions for high-dimensional time series data potentially sampled at different frequencies. The sparse-group LASSO estimator can take advantage of such time series data structures and outperforms the unstructured LASSO. We establish oracle inequalities for the sparse-group LASSO estimator within a framework that allows for the mixing processes and recognizes that the financial and the macroe…
Moment-Implied Densities
Suppose one uses a parametric density function based on the first four (conditional) moments to model risk. There are quite a few densities to choose from and depending on which is selected, one implicitly assumes very different tail behavior and very different feasible skewness/kurtosis combinations. Surprisingly, there is no systematic analysis of the tradeoff one faces. It is the purpose of the article to address this. We focus on the tail beh…
Central Bank Macroeconomic Forecasting During the Global Financial Crisis
This article documents macroeconomic forecasting during the global financial crisis by two key central banks: the European Central Bank and the Federal Reserve Bank of New York. The article is the result of a collaborative effort between staff at the two institutions, allowing us to study the time-stamped forecasts as they were made throughout the crisis. The analysis does not exclusively focus on point forecast performance. It also examines meth…
Should Macroeconomic Forecasters Use Daily Financial Data and How
We introduce easy-to-implement, regression-based methods for predicting quarterly real economic activity that use daily financial data and rely on forecast combinations of mixed data sampling (MIDAS) regressions. We also extract a novel small set of daily financial factors from a large panel of about 1000 daily financial assets. Our analysis is designed to elucidate the value of daily financial information and provide real-time forecast updates o…
Stock Market Volatility and Macroeconomic Fundamentals
We revisit the relation between stock market volatility and macroeconomic activity using a new class of component models that distinguish short-run from long-run movements. We formulate models with the long-term component driven by inflation and industrial production growth that are in terms of pseudo out-of-sample prediction for horizons of one quarter at par or outperform more traditional time series volatility models at longer horizons. Hence,…
Forecasting Professional Forecasters
Surveys of forecasters, containing respondents’ predictions of future values of key macroeconomic variables, receive a lot of attention in the financial press, from investors and from policy makers. They are apparently widely perceived to provide useful information about agents’ expectations. Nonetheless, these survey forecasts suffer from the crucial disadvantage that they are often quite stale, as they are released only infrequently. In this ar…
Midas Regressions
We explore mixed data sampling (henceforth MIDAS) regression models. The regressions involve time series data sampled at different frequencies. Volatility and related processes are our prime focus, though the regression method has wider applications in macroeconomics and finance, among other areas. The regressions combine recent developments regarding estimation of volatility and a not-so-recent literature on distributed lag models. We study vari…
Editors' Report 2003
Editors' Report 2002
Rolling-Sample Volatility Estimators
We propose extensions of the continuous record asymptotic analysis for rolling sample variance estimators developed for estimating the quadratic variation of asset returns, referred to as integrated or realized volatility. We treat integrated volatility as a continuous time stochastic process sampled at high frequencies and suggest rolling sample estimators which share many features with spot volatility estimators. We discuss asymptotically effic…
Editors' Report 2001
Some Econometric Recipes for High-Frequency Data Cooking
According to Ragnar Frisch (1933), econometrics involves the mutual penetration of quantitative economic theory and statistical observation. Today, econometric research rarely has all the ingredients spelled out in Frisch's definition. Most econometric models are either very structural, contrived, and unfortunately typically rejected or else they are statistical summaries of stylized data features and unfortunately difficult to link unambiguously…
[New Capabilities and Methods of the X-12-Arima Seasonal-Adjustment Program]
A Semiparametric Factor Model of Interest Rates and Tests of the Affine Term Structure
Many continuous-time term structure of interest rate models assume a factor structure where the drift and volatility functions are affine functions of the state-variable process. These models involve very specific parametric choices of factors and functional specifications of the drift and volatility. Moreover, under the affine term structure restrictions not all factors necessarily affect interest rates at all maturities simultaneously. This cla…
Seasonal Adjustment and Other Data Transformations
In this article, it is shown that the case for using optimal signal-extraction filters is not all that convincing once it is recognized that seasonal adjustment is typically not the only transformation applied to data. Seasonal adjustment is viewed as any general linear filter. All other data transformations are also assumed to be linear. Although optimal filters always dominate uniform filters, their dominance critically depends on performing se…
[Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process?]
Periodic Autoregressive Conditional Heteroscedasticity
Most high-frequency asset returns exhibit seasonal volatility patterns. This article proposes a new class of models featuring periodicity in conditional heteroscedasticity explicitly designed to capture the repetitive seasonal time variation in the second-order moments. This new class of periodic autoregressive conditional heteroscedasticity, or P-ARCH, models is directly related to the class of periodic autoregressive moving average (ARMA) model…
Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process
We investigate whether seasonal-adjustment procedures are, at least approximately, linear data transformations. This question was initially addressed by Young and is important with respect to many issues including estimation of regression models with seasonally adjusted data. We focus on the X-11 program and rely on simulation evidence, involving linear unobserved component autoregressive integrated moving average models. We define a set of prope…
On the Periodic Structure of the Business Cycle
This article tests whether an economic recovery is equally likely to occur in any month of the year. I test this hypothesis with a homogeneous Markov switching-regime model and use the turning-point dates for business cycles marked by the National Bureau of Economic Research and Romer. I tend to find unequal probabilities to switch from recession to expansions. In particular, the spring and the month of December appear to have higher incidence of…
[Bayesian Analysis of Stochastic Volatility Models]
Unit-Root Tests and the Statistical Pitfalls of Seasonal Adjustment
Unit-root tests applied to the postwar seasonally adjusted quarterly gross national product series strongly support the null hypothesis of the presence of a unit root in the data-generating process. Evidence reported here with seasonally unadjusted data is far less conclusive. It is explained why seasonal-adjustment procedures may alter the outcome of conventional tests
Y a-t-il des biais systématiques dans les annonces budgétaires canadiennes
Every year the Canadian government makes up a budget for the forthcoming fiscal year. During the budget process, projections are made of expenditures and receipts contingent upon predictions of key macroeconomic variables. Naturally, one expects that the budget deficit or surplus actually realized will differ from what was initially announced. Neither of the two major protagonists in the budget decision-making process, namely the Legislative and …
Seasonal Extraction in the Presence of Feedback
Time series seasonal extraction techniques are quite often applied in the context of a policy aimed at controlling the nonseasonal components of a time series. Monetary policies targeting the nonseasonal components of monetary aggregates are an example. Such policies can be studied as a quadratic optimal control model in which observations are contaminated by seasonal noise. Optimal extraction filters in such models do not correspond to univariat…
No prominent works on this page.
Seasonal Extraction in the Presence of Feedback
Time series seasonal extraction techniques are quite often applied in the context of a policy aimed at controlling the nonseasonal components of a time series. Monetary policies targeting the nonseasonal components of monetary aggregates are an example. Such policies can be studied as a quadratic optimal control model in which observations are contaminated by seasonal noise. Optimal extraction filters in such models do not correspond to univariat…
Y a-t-il des biais systématiques dans les annonces budgétaires canadiennes
Every year the Canadian government makes up a budget for the forthcoming fiscal year. During the budget process, projections are made of expenditures and receipts contingent upon predictions of key macroeconomic variables. Naturally, one expects that the budget deficit or surplus actually realized will differ from what was initially announced. Neither of the two major protagonists in the budget decision-making process, namely the Legislative and …
Unit-Root Tests and the Statistical Pitfalls of Seasonal Adjustment
Unit-root tests applied to the postwar seasonally adjusted quarterly gross national product series strongly support the null hypothesis of the presence of a unit root in the data-generating process. Evidence reported here with seasonally unadjusted data is far less conclusive. It is explained why seasonal-adjustment procedures may alter the outcome of conventional tests
On the Periodic Structure of the Business Cycle
This article tests whether an economic recovery is equally likely to occur in any month of the year. I test this hypothesis with a homogeneous Markov switching-regime model and use the turning-point dates for business cycles marked by the National Bureau of Economic Research and Romer. I tend to find unequal probabilities to switch from recession to expansions. In particular, the spring and the month of December appear to have higher incidence of…
[Bayesian Analysis of Stochastic Volatility Models]
[Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process?]
Periodic Autoregressive Conditional Heteroscedasticity
Most high-frequency asset returns exhibit seasonal volatility patterns. This article proposes a new class of models featuring periodicity in conditional heteroscedasticity explicitly designed to capture the repetitive seasonal time variation in the second-order moments. This new class of periodic autoregressive conditional heteroscedasticity, or P-ARCH, models is directly related to the class of periodic autoregressive moving average (ARMA) model…
Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process
We investigate whether seasonal-adjustment procedures are, at least approximately, linear data transformations. This question was initially addressed by Young and is important with respect to many issues including estimation of regression models with seasonally adjusted data. We focus on the X-11 program and rely on simulation evidence, involving linear unobserved component autoregressive integrated moving average models. We define a set of prope…
Seasonal Adjustment and Other Data Transformations
In this article, it is shown that the case for using optimal signal-extraction filters is not all that convincing once it is recognized that seasonal adjustment is typically not the only transformation applied to data. Seasonal adjustment is viewed as any general linear filter. All other data transformations are also assumed to be linear. Although optimal filters always dominate uniform filters, their dominance critically depends on performing se…
[New Capabilities and Methods of the X-12-Arima Seasonal-Adjustment Program]
A Semiparametric Factor Model of Interest Rates and Tests of the Affine Term Structure
Many continuous-time term structure of interest rate models assume a factor structure where the drift and volatility functions are affine functions of the state-variable process. These models involve very specific parametric choices of factors and functional specifications of the drift and volatility. Moreover, under the affine term structure restrictions not all factors necessarily affect interest rates at all maturities simultaneously. This cla…
Some Econometric Recipes for High-Frequency Data Cooking
According to Ragnar Frisch (1933), econometrics involves the mutual penetration of quantitative economic theory and statistical observation. Today, econometric research rarely has all the ingredients spelled out in Frisch's definition. Most econometric models are either very structural, contrived, and unfortunately typically rejected or else they are statistical summaries of stylized data features and unfortunately difficult to link unambiguously…
Rolling-Sample Volatility Estimators
We propose extensions of the continuous record asymptotic analysis for rolling sample variance estimators developed for estimating the quadratic variation of asset returns, referred to as integrated or realized volatility. We treat integrated volatility as a continuous time stochastic process sampled at high frequencies and suggest rolling sample estimators which share many features with spot volatility estimators. We discuss asymptotically effic…
Editors' Report 2001
Editors' Report 2002
Editors' Report 2003
Midas Regressions
We explore mixed data sampling (henceforth MIDAS) regression models. The regressions involve time series data sampled at different frequencies. Volatility and related processes are our prime focus, though the regression method has wider applications in macroeconomics and finance, among other areas. The regressions combine recent developments regarding estimation of volatility and a not-so-recent literature on distributed lag models. We study vari…
Forecasting Professional Forecasters
Surveys of forecasters, containing respondents’ predictions of future values of key macroeconomic variables, receive a lot of attention in the financial press, from investors and from policy makers. They are apparently widely perceived to provide useful information about agents’ expectations. Nonetheless, these survey forecasts suffer from the crucial disadvantage that they are often quite stale, as they are released only infrequently. In this ar…
Should Macroeconomic Forecasters Use Daily Financial Data and How
We introduce easy-to-implement, regression-based methods for predicting quarterly real economic activity that use daily financial data and rely on forecast combinations of mixed data sampling (MIDAS) regressions. We also extract a novel small set of daily financial factors from a large panel of about 1000 daily financial assets. Our analysis is designed to elucidate the value of daily financial information and provide real-time forecast updates o…
Stock Market Volatility and Macroeconomic Fundamentals
We revisit the relation between stock market volatility and macroeconomic activity using a new class of component models that distinguish short-run from long-run movements. We formulate models with the long-term component driven by inflation and industrial production growth that are in terms of pseudo out-of-sample prediction for horizons of one quarter at par or outperform more traditional time series volatility models at longer horizons. Hence,…
Moment-Implied Densities
Suppose one uses a parametric density function based on the first four (conditional) moments to model risk. There are quite a few densities to choose from and depending on which is selected, one implicitly assumes very different tail behavior and very different feasible skewness/kurtosis combinations. Surprisingly, there is no systematic analysis of the tradeoff one faces. It is the purpose of the article to address this. We focus on the tail beh…
Central Bank Macroeconomic Forecasting During the Global Financial Crisis
This article documents macroeconomic forecasting during the global financial crisis by two key central banks: the European Central Bank and the Federal Reserve Bank of New York. The article is the result of a collaborative effort between staff at the two institutions, allowing us to study the time-stamped forecasts as they were made throughout the crisis. The analysis does not exclusively focus on point forecast performance. It also examines meth…
Machine Learning Time Series Regressions With an Application to Nowcasting
This article introduces structured machine learning regressions for high-dimensional time series data potentially sampled at different frequencies. The sparse-group LASSO estimator can take advantage of such time series data structures and outperforms the unstructured LASSO. We establish oracle inequalities for the sparse-group LASSO estimator within a framework that allows for the mixing processes and recognizes that the financial and the macroe…
Panel data nowcasting
The paper uses structured machine learning regressions for nowcasting with panel data consisting of series sampled at different frequencies. Motivated by the problem of predicting corporate earnings for a large cross‐section of firms with macroeconomic, financial, and news time series sampled at different frequencies, we focus on the sparse‐group LASSO regularization which can take advantage of the mixed‐frequency time series panel data structure…
Econometrics (21 works) · Economics (18 works) · Mathematics (16 works) · Statistics (15 works) · Computer Science (13 works) · Monetary Policy and Economic Impact (13 works) · Financial Risk and Volatility Modeling (9 works) · Complex Systems and Time Series Analysis (7 works) · Market Dynamics and Volatility (7 works) · Seasonal adjustment (7 works)