Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2022.04.002
Nakahiro Yoshida
A brief overview of the theory of quasi-likelihood analysis (QLA) is given and its usefulness is demonstrated with applications to estimation for a volatility parameter of a semimartingale. A simplified version of the QLA is recalled. The role of non-degeneracy of a key index reflecting identifiability is highlighted. In an application of the QLA, the concept of global jump filters is introduced for precise estimation of the volatility parameter from the data contaminated with jumps.
{"title":"Quasi-likelihood analysis for nonlinear stochastic processes","authors":"Nakahiro Yoshida","doi":"10.1016/j.ecosta.2022.04.002","DOIUrl":"10.1016/j.ecosta.2022.04.002","url":null,"abstract":"<div><div>A brief overview of the theory of quasi-likelihood analysis (QLA) is given and its usefulness is demonstrated with applications to estimation for a volatility parameter of a semimartingale. A simplified version of the QLA is recalled. The role of non-degeneracy of a key index reflecting identifiability is highlighted. In an application of the QLA, the concept of global jump filters is introduced for precise estimation of the volatility parameter from the data contaminated with jumps.</div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 246-257"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143149853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2021.11.007
Francesco Giancaterini, Alain Hecq
The properties of Maximum Likelihood estimator in mixed causal and noncausal models with a generalized Student’s error process are reviewed. Several known existing methods are typically not applicable in the heavy-tailed framework. To this end, a new approach to make inference on causal and noncausal parameters in finite sample sizes is proposed. It exploits the empirical variance of the generalized Student’s , without the existence of population variance. Monte Carlo simulations show a good performance of the new variance construction for fat tail series. Finally, different existing approaches are compared using three empirical applications: the variation of daily COVID-19 deaths in Belgium, the monthly wheat prices, and the monthly inflation rate in Brazil.
{"title":"Inference in mixed causal and noncausal models with generalized Student’s t-distributions","authors":"Francesco Giancaterini, Alain Hecq","doi":"10.1016/j.ecosta.2021.11.007","DOIUrl":"10.1016/j.ecosta.2021.11.007","url":null,"abstract":"<div><div>The properties of Maximum Likelihood estimator in mixed causal and noncausal models with a generalized Student’s <span><math><mi>t</mi></math></span> error process are reviewed. Several known existing methods are typically not applicable in the heavy-tailed framework. To this end, a new approach to make inference on causal and noncausal parameters in finite sample sizes is proposed. It exploits the empirical variance of the generalized Student’s <span><math><mi>t</mi></math></span>, without the existence of population variance. Monte Carlo simulations show a good performance of the new variance construction for fat tail series. Finally, different existing approaches are compared using three empirical applications: the variation of daily COVID-19 deaths in Belgium, the monthly wheat prices, and the monthly inflation rate in Brazil.</div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 1-12"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79363862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2022.01.007
Seong-ho Lee , Yanyuan Ma , Xavier de Luna
Novel estimators of causal effects for categorical and continuous treatments are proposed by using an optimal covariate balancing strategy for inverse probability weighting. The resulting estimators are shown to be consistent and asymptotically normal for causal contrasts of interest, either when the model explaining the treatment assignment is correctly specified, or when the correct set of bases for the outcome models has been chosen and the assignment model is sufficiently rich. For the categorical treatment case, the estimator attains the semiparametric efficiency bound when all models are correctly specified. For the continuous case, the causal parameter of interest is a function of the treatment dose. The latter is not parametrized and the estimators proposed are shown to have bias and variance of the classical nonparametric rate. Asymptotic results are complemented with simulations illustrating the finite sample properties. A data analysis suggests a nonlinear effect of BMI on self-reported health decline among the elderly.
{"title":"Covariate balancing for causal inference on categorical and continuous treatments","authors":"Seong-ho Lee , Yanyuan Ma , Xavier de Luna","doi":"10.1016/j.ecosta.2022.01.007","DOIUrl":"10.1016/j.ecosta.2022.01.007","url":null,"abstract":"<div><div>Novel estimators of causal effects for categorical and continuous treatments are proposed by using an optimal covariate balancing strategy for inverse probability weighting. The resulting estimators are shown to be consistent and asymptotically normal for causal contrasts of interest, either when the model explaining the treatment assignment is correctly specified, or when the correct set of bases for the outcome models has been chosen and the assignment model is sufficiently rich. For the categorical treatment case, the estimator attains the semiparametric efficiency bound when all models are correctly specified. For the continuous case, the causal parameter of interest is a function of the treatment dose. The latter is not parametrized and the estimators proposed are shown to have bias and variance of the classical nonparametric rate. Asymptotic results are complemented with simulations illustrating the finite sample properties. A data analysis suggests a nonlinear effect of BMI on self-reported health decline among the elderly.</div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 304-329"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81971522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2021.02.005
{"title":"Erratum regarding missing Declaration of Competing Interest statements in previously published articles","authors":"","doi":"10.1016/j.ecosta.2021.02.005","DOIUrl":"10.1016/j.ecosta.2021.02.005","url":null,"abstract":"","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Page 338"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143149847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2022.09.003
David Gunawan , Robert Kohn , Minh Ngoc Tran
Density tempering (also called density annealing) is a sequential Monte Carlo approach to Bayesian inference for general state models which is an alternative to Markov chain Monte Carlo. When applied to state space models, it moves a collection of parameters and latent states (which are called particles) through a number of stages, with each stage having its own target distribution. The particles are initially generated from a distribution that is easy to sample from, e.g. the prior; the target at the final stage is the posterior distribution. Tempering is usually carried out either in batch mode, involving all the data at each stage, or sequentially with observations added at each stage, which is called data tempering. Efficient Markov moves for generating the parameters and states for each stage of particle based density tempering are proposed. This allows the proposed SMC methods to increase (scale up) the number of parameters and states that can be handled. Most current methods use a pseudo-marginal Markov move step with the states “integrated out”, and the parameters generated by a random walk proposal; although this strategy is general, it can be very inefficient when the states or parameters are high dimensional. By adding batch tempering at each stage, previous methods are extended to make data tempering more robust to outliers and structural changes for models with intractable likelihoods. The performance of the proposed methods is evaluated using univariate stochastic volatility models with outliers and structural breaks, and high dimensional factor stochastic volatility models having many parameters and many latent states.1
{"title":"Flexible and Robust Particle Tempering for State Space Models","authors":"David Gunawan , Robert Kohn , Minh Ngoc Tran","doi":"10.1016/j.ecosta.2022.09.003","DOIUrl":"10.1016/j.ecosta.2022.09.003","url":null,"abstract":"<div><div><span><span><span><span>Density tempering (also called density annealing) is a sequential Monte Carlo approach to </span>Bayesian inference<span> for general state models which is an alternative to Markov chain Monte Carlo. When applied to state space models, it moves a collection of parameters and latent states (which are called particles) through a number of stages, with each stage having its own </span></span>target distribution<span>. The particles are initially generated from a distribution that is easy to sample from, e.g. the prior; the target at the final stage is the posterior distribution. Tempering is usually carried out either in batch mode, involving all the data at each stage, or sequentially with observations added at each stage, which is called data tempering. Efficient Markov moves for generating the parameters and states for each stage of particle based density tempering are proposed. This allows the proposed SMC methods to increase (scale up) the number of parameters and states that can be handled. Most current methods use a pseudo-marginal Markov move step with the states “integrated out”, and the parameters generated by a </span></span>random walk<span><span> proposal; although this strategy is general, it can be very inefficient when the states or parameters are high dimensional. By adding batch tempering at each stage, previous methods are extended to make data tempering more robust to outliers and structural changes for models with intractable likelihoods. The performance of the proposed methods is evaluated using univariate </span>stochastic volatility models with outliers and structural breaks, and high dimensional factor stochastic volatility models having many parameters and many latent states.</span></span><span><span><sup>1</sup></span></span></div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 35-55"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80902225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2022.03.004
Pu Chen , Willi Semmler , Helmut Maurer
The effectiveness of monetary policies under delayed policy impacts are explored. Initially, in the context of a differential delay system, the macro-finance link is investigated. The nonlinear macro system with delays gives rise to a time-delayed optimal control problem. The optimality conditions are then analyzed, and the control problem is numerically solved by discretization and optimization methods. These solutions suggest that with too much delay, destabilizing financial conditions may emerge, rendering the policy ineffective. Then the possibility of asymmetric adjustments to a long-run steady-state, in a non-stationary environment is explored using a multi-regime cointegrated VAR (MRCIVAR) model for both an interest rate cut, and a non-interest rate cut regime. Though the rate cuts may not perform well with too long of a delay, given diverse shocks, monetary policy still performs better in a rate cut regime. Given the perils of deteriorating financial conditions, the better stabilization properties in a rate cut regime are empirically validated through data for European countries and the US.
{"title":"Delayed Monetary Policy Effects in a Multi-Regime Cointegrated VAR(MRCIVAR)","authors":"Pu Chen , Willi Semmler , Helmut Maurer","doi":"10.1016/j.ecosta.2022.03.004","DOIUrl":"10.1016/j.ecosta.2022.03.004","url":null,"abstract":"<div><div><span>The effectiveness of monetary policies under delayed policy impacts are explored. Initially, in the context of a </span>differential delay<span> system, the macro-finance link is investigated. The nonlinear macro system with delays gives rise to a time-delayed optimal control<span><span> problem. The optimality conditions are then analyzed, and the control problem is numerically solved by </span>discretization and optimization methods. These solutions suggest that with too much delay, destabilizing financial conditions may emerge, rendering the policy ineffective. Then the possibility of asymmetric adjustments to a long-run steady-state, in a non-stationary environment is explored using a multi-regime cointegrated VAR (MRCIVAR) model for both an interest rate cut, and a non-interest rate cut regime. Though the rate cuts may not perform well with too long of a delay, given diverse shocks, monetary policy still performs better in a rate cut regime. Given the perils of deteriorating financial conditions, the better stabilization properties in a rate cut regime are empirically validated through data for European countries and the US.</span></span></div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 105-134"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73411363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2021.02.002
{"title":"Erratum regarding missing Declaration of Competing Interest statements in previously published articles","authors":"","doi":"10.1016/j.ecosta.2021.02.002","DOIUrl":"10.1016/j.ecosta.2021.02.002","url":null,"abstract":"","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 332-333"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143149849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2021.09.002
Charles Chevalier , Serge Darolles
A new method is proposed for disentangling the systematic components from the idiosyncratic components of risk associated with trend-following strategies. A simple statistical approach combined with standard dimension reduction techniques enables to identify the common trending component of futures market prices. This methodology is applied to a large set of futures, covering all asset classes, to extract a common risk factor, called CoTrend. It is shown that common trends are higher for some cross-asset class pairs than for intra-asset class pairs, such as JPY/USD and Gold. This result is used to create sectors in a portfolio diversification context, especially for trend-following strategies. Additionally, the CoTrend factor helps understand arbitrage-based Hedge Fund strategies, which by essence are decorrelated from standard risk factors.
{"title":"Diversifying Trends","authors":"Charles Chevalier , Serge Darolles","doi":"10.1016/j.ecosta.2021.09.002","DOIUrl":"10.1016/j.ecosta.2021.09.002","url":null,"abstract":"<div><div>A new method is proposed for disentangling the systematic components from the idiosyncratic components of risk associated with trend-following strategies. A simple statistical approach combined with standard dimension reduction techniques enables to identify the common trending component of futures market prices. This methodology is applied to a large set of futures, covering all asset classes, to extract a common risk factor, called CoTrend. It is shown that common trends are higher for some cross-asset class pairs than for intra-asset class pairs, such as JPY/USD and Gold. This result is used to create sectors in a portfolio diversification context, especially for trend-following strategies. Additionally, the CoTrend factor helps understand arbitrage-based Hedge Fund strategies, which by essence are decorrelated from standard risk factors.</div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 56-79"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143150807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2022.04.004
Eliana Christou, Michael Grabchak
New methods for the estimation of the popular risk measures expected shortfall (ES) and Value-at-Risk (VaR) are introduced. These are based on a novel variant of composite quantile regression (CQR), which allows for the simultaneous estimation of quantiles at several levels at once. An extensive simulation study is performed, along with a data analysis based on two major US market indices and two financial sector stocks. The results suggest that the method has a good finite sample performance. This is the first methodology to use CQR for risk estimation.
{"title":"Risk Estimation With Composite Quantile Regression","authors":"Eliana Christou, Michael Grabchak","doi":"10.1016/j.ecosta.2022.04.004","DOIUrl":"10.1016/j.ecosta.2022.04.004","url":null,"abstract":"<div><div>New methods for the estimation of the popular risk measures expected shortfall (ES) and Value-at-Risk (VaR) are introduced. These are based on a novel variant of composite quantile regression (CQR), which allows for the simultaneous estimation of quantiles at several levels at once. An extensive simulation study is performed, along with a data analysis based on two major US market indices and two financial sector stocks. The results suggest that the method has a good finite sample performance. This is the first methodology to use CQR for risk estimation.</div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 166-179"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90063750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-01DOI: 10.1016/j.ecosta.2022.05.005
Fabrizio Cipollini , Giampiero M. Gallo
The issue of combining low– and high–frequency components of volatility is addressed within the class of Multiplicative Error Models both in the univariate and multivariate cases. Inference based on the Generalized Method of Moments is suggested, which has the advantage of not requiring a parametric choice for the error distribution. The application relates to several volatility market indices (US, Europe and East Asia, with interdependencies in the short–run components of absolute returns, realized kernel volatility and option–based implied volatility indices): a set of diagnostic tools is used to evaluate the evidence of a relevant low–frequency component across markets, also from a forecasting comparison perspective. The results show that the slow–moving component in the dynamics achieves a better fit to the data and allows for an interpretation of what moves the local average level of volatility.
{"title":"Multiplicative Error Models: 20 years on","authors":"Fabrizio Cipollini , Giampiero M. Gallo","doi":"10.1016/j.ecosta.2022.05.005","DOIUrl":"10.1016/j.ecosta.2022.05.005","url":null,"abstract":"<div><div>The issue of combining low– and high–frequency components of volatility is addressed within the class of Multiplicative Error Models both in the univariate and multivariate cases. Inference based on the Generalized Method of Moments is suggested, which has the advantage of not requiring a parametric choice for the error distribution. The application relates to several volatility market indices (US, Europe and East Asia, with interdependencies in the short–run components of absolute returns, realized kernel volatility and option–based implied volatility indices): a set of diagnostic tools is used to evaluate the evidence of a relevant low–frequency component across markets, also from a forecasting comparison perspective. The results show that the slow–moving component in the dynamics achieves a better fit to the data and allows for an interpretation of what moves the local average level of volatility.</div></div>","PeriodicalId":54125,"journal":{"name":"Econometrics and Statistics","volume":"33 ","pages":"Pages 209-229"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80450192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号