Abstract The article uses spline-based phase analysis to study the dynamics of a time series of low-frequency data on the values of a certain economic indicator. The approach includes two stages. At the first stage, the original series is approximated by a smooth twice-differentiable function. Natural cubic splines are used as an approximating function y y . Such splines have the smallest curvature over the observation interval compared to other possible functions that satisfy the choice criterion. At the second stage, a phase trajectory is constructed in ( t , y , y ′ ) left(t,y,y^{prime} ) -space, corresponding to the original time series, and a phase shadow as a projection of the phase trajectory onto the ( y , y ′ ) (y,y^{prime} ) -plane. The approach is applied to the values of GDP indicators for the G7 countries. The interrelation between phase shadow loops and cycles of economic indicators evolution is shown. The study also discusses the features, limitations and prospects for the use of spline-based phase analysis.
{"title":"Applying spline-based phase analysis to macroeconomic dynamics","authors":"Gadasina Lyudmila, V. Lyudmila","doi":"10.1515/demo-2022-0113","DOIUrl":"https://doi.org/10.1515/demo-2022-0113","url":null,"abstract":"Abstract The article uses spline-based phase analysis to study the dynamics of a time series of low-frequency data on the values of a certain economic indicator. The approach includes two stages. At the first stage, the original series is approximated by a smooth twice-differentiable function. Natural cubic splines are used as an approximating function y y . Such splines have the smallest curvature over the observation interval compared to other possible functions that satisfy the choice criterion. At the second stage, a phase trajectory is constructed in ( t , y , y ′ ) left(t,y,y^{prime} ) -space, corresponding to the original time series, and a phase shadow as a projection of the phase trajectory onto the ( y , y ′ ) (y,y^{prime} ) -plane. The approach is applied to the values of GDP indicators for the G7 countries. The interrelation between phase shadow loops and cycles of economic indicators evolution is shown. The study also discusses the features, limitations and prospects for the use of spline-based phase analysis.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"207 - 214"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49034759","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}
Abstract The paper provides a comparative empirical study of predictability of cryptocurrency returns and prices using econometrically justified robust inference methods. We present robust econometric analysis of predictive regressions incorporating factors, which were suggested by Liu, Y., & Tsyvinski, A. (2018). Risks and returns of cryptocurrency. NBER working paper no. 24877; Liu, Y., & Tsyvinski, A. (2021). Risks and returns of cryptocurrency. The Review of Financial Studies, 34(6), 2689–2727, as useful predictors for cryptocurrency returns, including cryptocurrency momentum, stock market factors, acceptance of Bitcoin, and Google trends measure of investors’ attention. Due to inherent heterogeneity and dependence properties of returns and other time series in financial and crypto markets, we provide the analysis of the predictive regressions using both heteroskedasticity and autocorrelation consistent (HAC) standard-errors and also the recently developed t t -statistic robust inference approaches, Ibragimov, R., & Müller, U. K. (2010). t-statistic based correlation and heterogeneity robust inference. Journal of Business and Economic Statistics, 28, 453–468; Ibragimov, R., & Müller, U. K. (2016). Inference with few heterogeneous clusters. Review of Economics and Statistics, 98, 83–96. We provide comparisons of robust predictive regression estimates between different cryptocurrencies and their corresponding risk and factor exposures. In general, the number of significant factors decreases as we use more robust t-tests, and the t-statistic robust inference approaches appear to perform better than the t-tests based on HAC standard errors in terms of pointing out interpretable economic conclusions. The results in this paper emphasize the importance of the use of robust inference approaches in the analysis of economic and financial data affected by the problems of heterogeneity and dependence.
{"title":"Predictability of cryptocurrency returns: evidence from robust tests","authors":"Siyun He, R. Ibragimov","doi":"10.1515/demo-2022-0111","DOIUrl":"https://doi.org/10.1515/demo-2022-0111","url":null,"abstract":"Abstract The paper provides a comparative empirical study of predictability of cryptocurrency returns and prices using econometrically justified robust inference methods. We present robust econometric analysis of predictive regressions incorporating factors, which were suggested by Liu, Y., & Tsyvinski, A. (2018). Risks and returns of cryptocurrency. NBER working paper no. 24877; Liu, Y., & Tsyvinski, A. (2021). Risks and returns of cryptocurrency. The Review of Financial Studies, 34(6), 2689–2727, as useful predictors for cryptocurrency returns, including cryptocurrency momentum, stock market factors, acceptance of Bitcoin, and Google trends measure of investors’ attention. Due to inherent heterogeneity and dependence properties of returns and other time series in financial and crypto markets, we provide the analysis of the predictive regressions using both heteroskedasticity and autocorrelation consistent (HAC) standard-errors and also the recently developed t t -statistic robust inference approaches, Ibragimov, R., & Müller, U. K. (2010). t-statistic based correlation and heterogeneity robust inference. Journal of Business and Economic Statistics, 28, 453–468; Ibragimov, R., & Müller, U. K. (2016). Inference with few heterogeneous clusters. Review of Economics and Statistics, 98, 83–96. We provide comparisons of robust predictive regression estimates between different cryptocurrencies and their corresponding risk and factor exposures. In general, the number of significant factors decreases as we use more robust t-tests, and the t-statistic robust inference approaches appear to perform better than the t-tests based on HAC standard errors in terms of pointing out interpretable economic conclusions. The results in this paper emphasize the importance of the use of robust inference approaches in the analysis of economic and financial data affected by the problems of heterogeneity and dependence.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"191 - 206"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41577622","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}
Abstract The Schwartz–Smith two-factor model is commonly used for pricing of derivatives in commodity markets. For estimating and forecasting the term structures of futures prices, the logarithm of commodity spot price is represented as the sum of short- and long-term factors being the unobservable state variables. The futures prices derived as functions of the spot price lead to the simultaneous set of measurement equations, which is used for joint estimation of unobservable state variables and the model parameters through a filtering procedure. We propose a modified model where the error terms in the measurement equations are assumed to be serially correlated. In addition, for comparative analysis, the modelling of the logarithmic returns of futures prices is also considered. Out-of-sample prediction performances of two proposed models were illustrated using European Unit Allowances (EUA) futures prices from January 2017 to April 2021. Historically, this period corresponds to the second half of Phase III, and the beginning of Phase IV of the European Union Emission Trading System (EU-ETS).
{"title":"On correlated measurement errors in the Schwartz–Smith two-factor model","authors":"J. Han, N. Kordzakhia, P. Shevchenko, S. Trück","doi":"10.1515/demo-2022-0106","DOIUrl":"https://doi.org/10.1515/demo-2022-0106","url":null,"abstract":"Abstract The Schwartz–Smith two-factor model is commonly used for pricing of derivatives in commodity markets. For estimating and forecasting the term structures of futures prices, the logarithm of commodity spot price is represented as the sum of short- and long-term factors being the unobservable state variables. The futures prices derived as functions of the spot price lead to the simultaneous set of measurement equations, which is used for joint estimation of unobservable state variables and the model parameters through a filtering procedure. We propose a modified model where the error terms in the measurement equations are assumed to be serially correlated. In addition, for comparative analysis, the modelling of the logarithmic returns of futures prices is also considered. Out-of-sample prediction performances of two proposed models were illustrated using European Unit Allowances (EUA) futures prices from January 2017 to April 2021. Historically, this period corresponds to the second half of Phase III, and the beginning of Phase IV of the European Union Emission Trading System (EU-ETS).","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"108 - 122"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49155566","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}
M. Mamonov, Christopher F. Parmeter, Artem B. Prokhorov
Abstract This review covers several of the core methodological and empirical developments surrounding stochastic frontier models that incorporate various new forms of dependence. Such models apply naturally to panels where cross-sectional observations on firm productivity correlate over time, but also in situations where various components of the error structure correlate between each other and with input variables. Ignoring such dependence patterns is known to lead to severe biases in the estimates of production functions and to incorrect inference.
{"title":"Dependence modeling in stochastic frontier analysis","authors":"M. Mamonov, Christopher F. Parmeter, Artem B. Prokhorov","doi":"10.1515/demo-2022-0107","DOIUrl":"https://doi.org/10.1515/demo-2022-0107","url":null,"abstract":"Abstract This review covers several of the core methodological and empirical developments surrounding stochastic frontier models that incorporate various new forms of dependence. Such models apply naturally to panels where cross-sectional observations on firm productivity correlate over time, but also in situations where various components of the error structure correlate between each other and with input variables. Ignoring such dependence patterns is known to lead to severe biases in the estimates of production functions and to incorrect inference.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"123 - 144"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41657688","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}
Abstract We derive a novel stochastic representation of exchangeable Marshall–Olkin distributions based on their death-counting processes. We show that these processes are Markov. Furthermore, we provide a numerically stable approximation of their infinitesimal generator matrices in the extendible case. This approach uses integral representations of Bernstein functions to calculate the generator’s first row, and then uses a recursion to calculate the remaining rows. Combining the Markov representation with the numerically stable approximation of corresponding generators allows us to sample extendible Marshall–Olkin distributions with a flexible simulation algorithm derived from known Markov sampling strategies. Finally, we benchmark an implementation of this Markov-based simulation algorithm against alternative simulation algorithms based on the Lévy frailty model, the Arnold model, and the exogenous shock model.
{"title":"Implementing Markovian models for extendible Marshall–Olkin distributions","authors":"Henrik Sloot","doi":"10.1515/demo-2022-0151","DOIUrl":"https://doi.org/10.1515/demo-2022-0151","url":null,"abstract":"Abstract We derive a novel stochastic representation of exchangeable Marshall–Olkin distributions based on their death-counting processes. We show that these processes are Markov. Furthermore, we provide a numerically stable approximation of their infinitesimal generator matrices in the extendible case. This approach uses integral representations of Bernstein functions to calculate the generator’s first row, and then uses a recursion to calculate the remaining rows. Combining the Markov representation with the numerically stable approximation of corresponding generators allows us to sample extendible Marshall–Olkin distributions with a flexible simulation algorithm derived from known Markov sampling strategies. Finally, we benchmark an implementation of this Markov-based simulation algorithm against alternative simulation algorithms based on the Lévy frailty model, the Arnold model, and the exogenous shock model.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"308 - 343"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44552593","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}
Abstract This article accounts for multivariate dependence of the variable of policy interest in dynamic panel data models by disentangling the two sources of intertemporal dependence: one from the effect of the policy variable and the other from mean reversion. In a situation where intensity of the policy varies over time, we estimate the unconditional mean in the autoregressive process as a function of the agent’s characteristics and the policy intensity. Comparison of the fitted values of the unconditional mean under different values of the policy intensity enables identification of the policy effect cleared of mean reversion. The approach is relevant for measuring the effect of reforms, which use an intertemporal incentive where intensity of the reform varies over time. The empirical part of the article assesses the effect of hospital financing reform based on incentive contracts, related to the observed quality of services at Medicare hospitals in 2013–2019. We find a direct association between prior quality and quality improvement owing to the reform. Our result reassesses a stylized fact in the literature, which asserts that a pay-for-performance incentive leads to greater improvements at hospitals with lower baseline quality.
{"title":"Disentangling the impact of mean reversion in estimating policy response with dynamic panels","authors":"G. Besstremyannaya, S. Golovan","doi":"10.1515/demo-2022-0104","DOIUrl":"https://doi.org/10.1515/demo-2022-0104","url":null,"abstract":"Abstract This article accounts for multivariate dependence of the variable of policy interest in dynamic panel data models by disentangling the two sources of intertemporal dependence: one from the effect of the policy variable and the other from mean reversion. In a situation where intensity of the policy varies over time, we estimate the unconditional mean in the autoregressive process as a function of the agent’s characteristics and the policy intensity. Comparison of the fitted values of the unconditional mean under different values of the policy intensity enables identification of the policy effect cleared of mean reversion. The approach is relevant for measuring the effect of reforms, which use an intertemporal incentive where intensity of the reform varies over time. The empirical part of the article assesses the effect of hospital financing reform based on incentive contracts, related to the observed quality of services at Medicare hospitals in 2013–2019. We find a direct association between prior quality and quality improvement owing to the reform. Our result reassesses a stylized fact in the literature, which asserts that a pay-for-performance incentive leads to greater improvements at hospitals with lower baseline quality.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"58 - 86"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48456996","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}
Abstract We provide an exact simulation algorithm for bivariate Archimax copulas, including instances with negative association. In contrast to existing simulation approaches, the feasibility of our algorithm is directly linked to the availability of an exact simulation algorithm for the probability measure described by the derivative of the parameterizing Pickands dependence function. We demonstrate that this hypothesis is satisfied in many cases of interest and, in particular, it is satisfied for piece-wise constant Pickands dependence functions, which can approximate the general case to a given level of desired accuracy. Finally, the algorithm can be leveraged to an exact simulation algorithm for bivariate copulas associated with max-infinitely divisible random vectors whose exponent measure has norm-symmetric survival function, so-called reciprocal Archimax copulas.
{"title":"About the exact simulation of bivariate (reciprocal) Archimax copulas","authors":"Jan-Frederik Mai","doi":"10.1515/demo-2022-0102","DOIUrl":"https://doi.org/10.1515/demo-2022-0102","url":null,"abstract":"Abstract We provide an exact simulation algorithm for bivariate Archimax copulas, including instances with negative association. In contrast to existing simulation approaches, the feasibility of our algorithm is directly linked to the availability of an exact simulation algorithm for the probability measure described by the derivative of the parameterizing Pickands dependence function. We demonstrate that this hypothesis is satisfied in many cases of interest and, in particular, it is satisfied for piece-wise constant Pickands dependence functions, which can approximate the general case to a given level of desired accuracy. Finally, the algorithm can be leveraged to an exact simulation algorithm for bivariate copulas associated with max-infinitely divisible random vectors whose exponent measure has norm-symmetric survival function, so-called reciprocal Archimax copulas.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"29 - 47"},"PeriodicalIF":0.7,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43159680","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}
Abstract A combinatorial proof of the Gaussian product inequality (GPI) is given under the assumption that each component of a centered Gaussian random vector X = ( X 1 , … , X d ) {boldsymbol{X}}=left({X}_{1},ldots ,{X}_{d}) of arbitrary length can be written as a linear combination, with coefficients of identical sign, of the components of a standard Gaussian random vector. This condition on X {boldsymbol{X}} is shown to be strictly weaker than the assumption that the density of the random vector ( ∣ X 1 ∣ , … , ∣ X d ∣ ) left(| {X}_{1}| ,ldots ,| {X}_{d}| ) is multivariate totally positive of order 2, abbreviated MTP 2 {text{MTP}}_{2} , for which the GPI is already known to hold. Under this condition, the paper highlights a new link between the GPI and the monotonicity of a certain ratio of gamma functions.
{"title":"A combinatorial proof of the Gaussian product inequality beyond the MTP2 case","authors":"C. Genest, Frédéric Ouimet","doi":"10.1515/demo-2022-0116","DOIUrl":"https://doi.org/10.1515/demo-2022-0116","url":null,"abstract":"Abstract A combinatorial proof of the Gaussian product inequality (GPI) is given under the assumption that each component of a centered Gaussian random vector X = ( X 1 , … , X d ) {boldsymbol{X}}=left({X}_{1},ldots ,{X}_{d}) of arbitrary length can be written as a linear combination, with coefficients of identical sign, of the components of a standard Gaussian random vector. This condition on X {boldsymbol{X}} is shown to be strictly weaker than the assumption that the density of the random vector ( ∣ X 1 ∣ , … , ∣ X d ∣ ) left(| {X}_{1}| ,ldots ,| {X}_{d}| ) is multivariate totally positive of order 2, abbreviated MTP 2 {text{MTP}}_{2} , for which the GPI is already known to hold. Under this condition, the paper highlights a new link between the GPI and the monotonicity of a certain ratio of gamma functions.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"236 - 244"},"PeriodicalIF":0.7,"publicationDate":"2021-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48075039","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}
Abstract Modeling the error terms in stochastic frontier models of production systems requires multivariate distributions with certain characteristics. We argue that canonical vine copulas offer a natural way to model the pairwise dependence between the two main error types that arise in production systems with multiple inputs. We introduce a vine copula construction that permits dependence between the magnitude (but not the sign) of the errors. By using a recently proposed family of copulas, we show how to construct a simulated likelihood based on C-vines. We discuss issues that arise in the estimation of such models and outline why such models better reflect the dependencies that arise in practice. Monte Carlo simulations and a classic empirical application to electricity generation plants illustrate the utility of the proposed approach.
{"title":"Technical and allocative inefficiency in production systems: a vine copula approach","authors":"Jian Zhai, R. James, Artem Prokhorov","doi":"10.2139/ssrn.3889783","DOIUrl":"https://doi.org/10.2139/ssrn.3889783","url":null,"abstract":"Abstract Modeling the error terms in stochastic frontier models of production systems requires multivariate distributions with certain characteristics. We argue that canonical vine copulas offer a natural way to model the pairwise dependence between the two main error types that arise in production systems with multiple inputs. We introduce a vine copula construction that permits dependence between the magnitude (but not the sign) of the errors. By using a recently proposed family of copulas, we show how to construct a simulated likelihood based on C-vines. We discuss issues that arise in the estimation of such models and outline why such models better reflect the dependencies that arise in practice. Monte Carlo simulations and a classic empirical application to electricity generation plants illustrate the utility of the proposed approach.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"145 - 158"},"PeriodicalIF":0.7,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49611130","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}
Marija Tepegjozova, Jing Zhou, G. Claeskens, C. Czado
Abstract Quantile regression is a field with steadily growing importance in statistical modeling. It is a complementary method to linear regression, since computing a range of conditional quantile functions provides more accurate modeling of the stochastic relationship among variables, especially in the tails. We introduce a nonrestrictive and highly flexible nonparametric quantile regression approach based on C- and D-vine copulas. Vine copulas allow for separate modeling of marginal distributions and the dependence structure in the data and can be expressed through a graphical structure consisting of a sequence of linked trees. This way, we obtain a quantile regression model that overcomes typical issues of quantile regression such as quantile crossings or collinearity, the need for transformations and interactions of variables. Our approach incorporates a two-step ahead ordering of variables, by maximizing the conditional log-likelihood of the tree sequence, while taking into account the next two tree levels. We show that the nonparametric conditional quantile estimator is consistent. The performance of the proposed methods is evaluated in both low- and high-dimensional settings using simulated and real-world data. The results support the superior prediction ability of the proposed models.
{"title":"Nonparametric C- and D-vine-based quantile regression","authors":"Marija Tepegjozova, Jing Zhou, G. Claeskens, C. Czado","doi":"10.1515/demo-2022-0100","DOIUrl":"https://doi.org/10.1515/demo-2022-0100","url":null,"abstract":"Abstract Quantile regression is a field with steadily growing importance in statistical modeling. It is a complementary method to linear regression, since computing a range of conditional quantile functions provides more accurate modeling of the stochastic relationship among variables, especially in the tails. We introduce a nonrestrictive and highly flexible nonparametric quantile regression approach based on C- and D-vine copulas. Vine copulas allow for separate modeling of marginal distributions and the dependence structure in the data and can be expressed through a graphical structure consisting of a sequence of linked trees. This way, we obtain a quantile regression model that overcomes typical issues of quantile regression such as quantile crossings or collinearity, the need for transformations and interactions of variables. Our approach incorporates a two-step ahead ordering of variables, by maximizing the conditional log-likelihood of the tree sequence, while taking into account the next two tree levels. We show that the nonparametric conditional quantile estimator is consistent. The performance of the proposed methods is evaluated in both low- and high-dimensional settings using simulated and real-world data. The results support the superior prediction ability of the proposed models.","PeriodicalId":43690,"journal":{"name":"Dependence Modeling","volume":"10 1","pages":"1 - 21"},"PeriodicalIF":0.7,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43773203","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：