Three particular models of dependence in asset returns with non-Gaussian marginals are investigated on daily return data for sector exchange traded funds. The first model is a full rank Gaussian copula (FGC). The second models returns as a linear mixture of independent Levy processes (LML). The third correlates Gaussian components in a variance gamma representation (VGC). On a number of occasions all three models are comparable. More generally, in some by sectors, we get a superior performance from the LML model followed by VGC and FGC as measured by the proportion of portfolios with higher p-values. There are occasions when the VGC and FGC dominate. The concept of local correlation is introduced to help discriminate between the models and it is observed that the LML models display higher levels of local correlation especially in the tails when compared with either the VGC or FGC models.
{"title":"Three Non-Gaussian Models of Dependence in Returns","authors":"D. Madan","doi":"10.2139/ssrn.2635629","DOIUrl":"https://doi.org/10.2139/ssrn.2635629","url":null,"abstract":"Three particular models of dependence in asset returns with non-Gaussian marginals are investigated on daily return data for sector exchange traded funds. The first model is a full rank Gaussian copula (FGC). The second models returns as a linear mixture of independent Levy processes (LML). The third correlates Gaussian components in a variance gamma representation (VGC). On a number of occasions all three models are comparable. More generally, in some by sectors, we get a superior performance from the LML model followed by VGC and FGC as measured by the proportion of portfolios with higher p-values. There are occasions when the VGC and FGC dominate. The concept of local correlation is introduced to help discriminate between the models and it is observed that the LML models display higher levels of local correlation especially in the tails when compared with either the VGC or FGC models.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125188647","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}
Recent periods of market turbulence and stress have created considerable interest in credible alternatives to traditional asset allocation methodologies. It would be preferred if portfolios can be decomposed into components that can be directly connected to independent risks and individually rewarded by the market for their level of risk. This can be achieved through factor-based investing, which relies on the observation that most return and risk characteristics for all asset classes can be well explained by particular building blocks, or factors.We describe main features of factors, factor investing and factor models, with emphasis placed on practical topics such as selection of significant factors associated to specific asset classes, differentiating between factors, anomalies or stylized facts, and preference for composite portfolios based on combining factors. We have also analyzed implementation details and the factor risk parity strategy.Then we consider improvements to factor-based investing through regime switching and sensitivity analysis. We present theoretical and practical frameworks for Markov switching models and for sensitivity analysis, and rely on representative examples to illustrate the benefits of efficiently incorporating regimes and sensitivity analysis into portfolio management.The final section describes features of good testing procedures for portfolio behavior and performance, in contrasts with possible testing pitfalls.
{"title":"Better Investing Through Factors, Regimes and Sensitivity Analysis","authors":"Cristian Homescu","doi":"10.2139/ssrn.2557236","DOIUrl":"https://doi.org/10.2139/ssrn.2557236","url":null,"abstract":"Recent periods of market turbulence and stress have created considerable interest in credible alternatives to traditional asset allocation methodologies. It would be preferred if portfolios can be decomposed into components that can be directly connected to independent risks and individually rewarded by the market for their level of risk. This can be achieved through factor-based investing, which relies on the observation that most return and risk characteristics for all asset classes can be well explained by particular building blocks, or factors.We describe main features of factors, factor investing and factor models, with emphasis placed on practical topics such as selection of significant factors associated to specific asset classes, differentiating between factors, anomalies or stylized facts, and preference for composite portfolios based on combining factors. We have also analyzed implementation details and the factor risk parity strategy.Then we consider improvements to factor-based investing through regime switching and sensitivity analysis. We present theoretical and practical frameworks for Markov switching models and for sensitivity analysis, and rely on representative examples to illustrate the benefits of efficiently incorporating regimes and sensitivity analysis into portfolio management.The final section describes features of good testing procedures for portfolio behavior and performance, in contrasts with possible testing pitfalls.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115913087","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}
During the first decades following Black and Scholes, the quantitative finance have been focus mainly on the modeling of the volatility. Indeed, the expansion of derivatives product brought some liquidity regarding this parameter. The implied volatility is the reflect of market convention for the vanilla premium but are also an extension of the industry focus. If the volatility modelling is difficult, the correlation modelling stage at another level. In fact, many market participant portfolios were attached to correlation risk - market participants such as insurance companies and pension funds - therefore, banks innovated solutions which imply transfer of the risk. A huge range of products such as Dispersion, Correlation Swap, Basket Option, Best Of and Worst Of have been introduced and sold with more or less popularity. Banks were willing to take the risk but they needed more elaborate model in order to capture the correlation risk. If the business pressure was to trade and deal with the residual risk with conventional correlation framework (deterministic term structure), after the default of Lehman Brother, the Trading Desk had to transfer the pressure and challenge quants in order to have the ability to hedge their correlation exposure. In this paper, we enumerate industry innovations on correlation modeling and discuss some improvements and market understanding of it.
{"title":"Correlation, Where are You? Where are We? Update on Correlation Modeling","authors":"Christian Kamtchueng","doi":"10.2139/ssrn.2494939","DOIUrl":"https://doi.org/10.2139/ssrn.2494939","url":null,"abstract":"During the first decades following Black and Scholes, the quantitative finance have been focus mainly on the modeling of the volatility. Indeed, the expansion of derivatives product brought some liquidity regarding this parameter. The implied volatility is the reflect of market convention for the vanilla premium but are also an extension of the industry focus. If the volatility modelling is difficult, the correlation modelling stage at another level. In fact, many market participant portfolios were attached to correlation risk - market participants such as insurance companies and pension funds - therefore, banks innovated solutions which imply transfer of the risk. A huge range of products such as Dispersion, Correlation Swap, Basket Option, Best Of and Worst Of have been introduced and sold with more or less popularity. Banks were willing to take the risk but they needed more elaborate model in order to capture the correlation risk. If the business pressure was to trade and deal with the residual risk with conventional correlation framework (deterministic term structure), after the default of Lehman Brother, the Trading Desk had to transfer the pressure and challenge quants in order to have the ability to hedge their correlation exposure. In this paper, we enumerate industry innovations on correlation modeling and discuss some improvements and market understanding of it.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129412890","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}
DV01, the dollar value impact of a 1 basis point change in a yield curve is one of the most basic and widely used measures of market risk. Similar quantities and sensitivities have been defined for other parameters or “risk drivers” for a given, fixed model. In this present work we provide a meaningful and intuitive notion of Model01, which attempts to capture the analogue of a “1 basis point” bump in the space of models, beyond simple parametric changes. Importantly, our technique successfully calibrates each of these bumped models to the same set of liquid reference contracts. This turns out to be fundamental for a proper assessment of Model01 among exotic portfolios, and allows a meaningful comparison of the Model01 dollar value against the total reference price of a portfolio. Using the same procedure, it is possible to compute Model01 for single trades or portfolios of multiple trades, across different asset types and underliers, due to the flexibility of Weighted Monte Carlo techniques, on which it relies. The literature on quantification of model risk is limited. We will highlight the main features of R. Cont on model uncertainty and P. Glasserman and X. Xu on model risk, and compare Model01 against these approaches. The contributions from the present effort are manifold. We put forward the Hellinger distance as a more intuitive and genuine metric in the space of probability distributions, in contrast with relative entropy, which is more commonly used in the financial literature. We highlight connections between Model01 and an active area of research called information-geometry. This field applies the methods of differential geometry to the problem of statistical inference, and in particular, the problem of defining intuitive notions of distances across probability distributions. The problem at hand is strongly related, with a meaningful quantification of model uncertainty calling for a normalized measure of distances in the space of models. A fruitful connection and further explorations of these ideas should come then as no surprise. We motivate an interpretation of relative entropy as a distance squared. We employ this to analyze P. Glasserman and X. Xu techniques and cast them in rescaled units, revealing a linear dependence of their risk profiles which can be explained and proved. To the authors' best knowledge, these contributions represent novel undertakings in the financial literature, with the Hellinger distance, the interpretation of relative entropy and the introduction of information-geometry techniques being put forward in the context of model sensitivity for the first time in this present work. We apply the techniques of information geometry to shed light into relative entropy and the Hellinger distance, and reveal a natural Riemannian geometric structure in the parameter space of the alternative, bumped models used to compute Model01. The application of these concepts further enriches the interpretation of our results. Armed
{"title":"Model01: Quantifying the Risk of Incremental Model Changes","authors":"D. Abasto, Mark P. Kust","doi":"10.2139/ssrn.2492256","DOIUrl":"https://doi.org/10.2139/ssrn.2492256","url":null,"abstract":"DV01, the dollar value impact of a 1 basis point change in a yield curve is one of the most basic and widely used measures of market risk. Similar quantities and sensitivities have been defined for other parameters or “risk drivers” for a given, fixed model. In this present work we provide a meaningful and intuitive notion of Model01, which attempts to capture the analogue of a “1 basis point” bump in the space of models, beyond simple parametric changes. Importantly, our technique successfully calibrates each of these bumped models to the same set of liquid reference contracts. This turns out to be fundamental for a proper assessment of Model01 among exotic portfolios, and allows a meaningful comparison of the Model01 dollar value against the total reference price of a portfolio. Using the same procedure, it is possible to compute Model01 for single trades or portfolios of multiple trades, across different asset types and underliers, due to the flexibility of Weighted Monte Carlo techniques, on which it relies. The literature on quantification of model risk is limited. We will highlight the main features of R. Cont on model uncertainty and P. Glasserman and X. Xu on model risk, and compare Model01 against these approaches. The contributions from the present effort are manifold. We put forward the Hellinger distance as a more intuitive and genuine metric in the space of probability distributions, in contrast with relative entropy, which is more commonly used in the financial literature. We highlight connections between Model01 and an active area of research called information-geometry. This field applies the methods of differential geometry to the problem of statistical inference, and in particular, the problem of defining intuitive notions of distances across probability distributions. The problem at hand is strongly related, with a meaningful quantification of model uncertainty calling for a normalized measure of distances in the space of models. A fruitful connection and further explorations of these ideas should come then as no surprise. We motivate an interpretation of relative entropy as a distance squared. We employ this to analyze P. Glasserman and X. Xu techniques and cast them in rescaled units, revealing a linear dependence of their risk profiles which can be explained and proved. To the authors' best knowledge, these contributions represent novel undertakings in the financial literature, with the Hellinger distance, the interpretation of relative entropy and the introduction of information-geometry techniques being put forward in the context of model sensitivity for the first time in this present work. We apply the techniques of information geometry to shed light into relative entropy and the Hellinger distance, and reveal a natural Riemannian geometric structure in the parameter space of the alternative, bumped models used to compute Model01. The application of these concepts further enriches the interpretation of our results. Armed ","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115277192","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}
We develop methods for Bayesian model averaging (BMA) or selection (BMS) in Panel Vector Autoregressions (PVARs). Our approach allows us to select between or average over all possible combinations of restricted PVARs where the restrictions involve interdependencies between and heterogeneities across cross-sectional units. The resulting BMA framework can find a parsimonious PVAR specification, thus dealing with overparameterization concerns. We use these methods in an application involving the euro area sovereign debt crisis and show that our methods perform better than alternatives. Our findings contradict a simple view of the sovereign debt crisis which divides the euro zone into groups of core and peripheral countries and worries about financial contagion within the latter group.
{"title":"Model Uncertainty in Panel Vector Autoregressive Models","authors":"G. Koop, Dimitris Korobilis","doi":"10.2139/ssrn.2487540","DOIUrl":"https://doi.org/10.2139/ssrn.2487540","url":null,"abstract":"We develop methods for Bayesian model averaging (BMA) or selection (BMS) in Panel Vector Autoregressions (PVARs). Our approach allows us to select between or average over all possible combinations of restricted PVARs where the restrictions involve interdependencies between and heterogeneities across cross-sectional units. The resulting BMA framework can find a parsimonious PVAR specification, thus dealing with overparameterization concerns. We use these methods in an application involving the euro area sovereign debt crisis and show that our methods perform better than alternatives. Our findings contradict a simple view of the sovereign debt crisis which divides the euro zone into groups of core and peripheral countries and worries about financial contagion within the latter group.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125179380","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}
The realized power variations with even order of a discretely observed semi-martingale have been widely studied in literature, due to some important applications in finance, for example, estimating the integrated volatility and integrated quarticity. However, few works have paid attention to the realized power variations whose power indices are odd. In this paper, we derive some limit theorems for realized variations with odd functions of an Ito semi-martingale on the fixed time interval [0,T], observed discretely at a high frequency. In the continuous case, unlike the realized power variations of even order, for example the quadratic variation, they converge only in distribution (stably) after multiplied by some appropriate factors, which are related to the length of the sampling interval, and the limiting processes consist of centered Wiener integrals and Riemann integrals that play a role as asymptotic biases. The limit theorems for the general case containing jumps have also been derived. An important application of the result is to measure the realized skewness with high frequency data. Simulation studies for various models have been investigated. Finally, we provide some real applications.
{"title":"Higher Order Realized Power Variations of Semi-Martingales with Applications","authors":"Yuta Koike, Zhi Liu","doi":"10.2139/ssrn.2438711","DOIUrl":"https://doi.org/10.2139/ssrn.2438711","url":null,"abstract":"The realized power variations with even order of a discretely observed semi-martingale have been widely studied in literature, due to some important applications in finance, for example, estimating the integrated volatility and integrated quarticity. However, few works have paid attention to the realized power variations whose power indices are odd. In this paper, we derive some limit theorems for realized variations with odd functions of an Ito semi-martingale on the fixed time interval [0,T], observed discretely at a high frequency. In the continuous case, unlike the realized power variations of even order, for example the quadratic variation, they converge only in distribution (stably) after multiplied by some appropriate factors, which are related to the length of the sampling interval, and the limiting processes consist of centered Wiener integrals and Riemann integrals that play a role as asymptotic biases. The limit theorems for the general case containing jumps have also been derived. An important application of the result is to measure the realized skewness with high frequency data. Simulation studies for various models have been investigated. Finally, we provide some real applications.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128349178","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}
The paper studies inference in nonlinear models where identification loss presents in multiple parts of the parameter space. For uniform inference, we develop a local limit theory that models mixed identification strength. Building on this non-standard asymptotic approximation, we suggest robust tests and confidence intervals in the presence of non-identified and weakly identified nuisance parameters. In particular, this covers applications where some nuisance parameters are non-identified under the null (Davies (1977, 1987)) and some nuisance parameters are subject to a full range of identification strength. The asymptotic results involve both inconsistent estimators that depend on a localization parameter and consistent estimators with different rates of convergence. A sequential argument is used to peel the criterion function based on identification strength of the parameters. The robust test is uniformly valid and non-conservative.
{"title":"Uniform Inference in Nonlinear Models with Mixed Identification Strength","authors":"Xu Cheng","doi":"10.2139/ssrn.2435179","DOIUrl":"https://doi.org/10.2139/ssrn.2435179","url":null,"abstract":"The paper studies inference in nonlinear models where identification loss presents in multiple parts of the parameter space. For uniform inference, we develop a local limit theory that models mixed identification strength. Building on this non-standard asymptotic approximation, we suggest robust tests and confidence intervals in the presence of non-identified and weakly identified nuisance parameters. In particular, this covers applications where some nuisance parameters are non-identified under the null (Davies (1977, 1987)) and some nuisance parameters are subject to a full range of identification strength. The asymptotic results involve both inconsistent estimators that depend on a localization parameter and consistent estimators with different rates of convergence. A sequential argument is used to peel the criterion function based on identification strength of the parameters. The robust test is uniformly valid and non-conservative.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122131589","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}
In this paper, we propose a likelihood ratio and Markov chain based method to evaluate density forecasting. This method can jointly evaluate the unconditional forecasted distribution and dependence of the outcomes. This method is an extension of the widely applied evaluation method for interval forecasting proposed by Christoffersen (1998). It is also a more refined approach than the pure contingency table based density forecasting method in Wallis (2003). We show that our method has very high power against incorrect forecasting distributions and dependence. Moreover, the straightforwardness and ease of application of this joint test provide a high potentiality for further applications in both financial and economical areas.
{"title":"A Likelihood Ratio and Markov Chain Based Method to Evaluate Density Forecasting","authors":"Yushu Li, Jonas Andersson","doi":"10.2139/ssrn.2416269","DOIUrl":"https://doi.org/10.2139/ssrn.2416269","url":null,"abstract":"In this paper, we propose a likelihood ratio and Markov chain based method to evaluate density forecasting. This method can jointly evaluate the unconditional forecasted distribution and dependence of the outcomes. This method is an extension of the widely applied evaluation method for interval forecasting proposed by Christoffersen (1998). It is also a more refined approach than the pure contingency table based density forecasting method in Wallis (2003). We show that our method has very high power against incorrect forecasting distributions and dependence. Moreover, the straightforwardness and ease of application of this joint test provide a high potentiality for further applications in both financial and economical areas.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115320835","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}
We introduce a new practical data-intensive method to generate/discover consistent finite representative collections of plausible yet severe macroprudential, microprudential, book-specific, and individual obligor/instrument scenarios. These scenarios are conditioned on current information (including current macroeconomic, index, industry and instrument/obligor-specific information), and can be conditioned on partial future scenario specifications as well (to accommodate regulatory stress testing requirements, for example, the CCAR requirements for banks, the projections of economists, or senior management). Our method is scalable, is designed to work with limited training data, can incorporate the fat-tailed and mutually dependent behavior that is characteristic of many financial quantities, and can reflect model misspecification risk.
{"title":"A Method to Find Diverse and Manageable Sets of Plausible Yet Severe Financial Scenarios","authors":"Craig Friedman, Yangyong Zhang","doi":"10.2139/ssrn.2379083","DOIUrl":"https://doi.org/10.2139/ssrn.2379083","url":null,"abstract":"We introduce a new practical data-intensive method to generate/discover consistent finite representative collections of plausible yet severe macroprudential, microprudential, book-specific, and individual obligor/instrument scenarios. These scenarios are conditioned on current information (including current macroeconomic, index, industry and instrument/obligor-specific information), and can be conditioned on partial future scenario specifications as well (to accommodate regulatory stress testing requirements, for example, the CCAR requirements for banks, the projections of economists, or senior management). Our method is scalable, is designed to work with limited training data, can incorporate the fat-tailed and mutually dependent behavior that is characteristic of many financial quantities, and can reflect model misspecification risk.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"285 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122091661","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}
This paper examines the extent to which large swings of sovereign yields in euro area countries during the sovereign debt crisis can be attributed to fundamentals. We focus on the inherent uncertainty in bond yield models, which is often overlooked in the literature. We show that the outcomes are strongly affected by modeling choices with regard to i) the confidence bands for the model prediction, ii) the assumption whether the model coefficients are similar across countries or not, iii) the sample selection, iv) the inclusion of financial variables and v) the choice of time-varying coefficients. These choices affect the explanatory power of macro fundamentals and the extent of mispricing. We find substantial misalignment compared to fundamentals for Greek yields, in most specifications also for Portugal and Ireland, but for the other EMU countries, including Spain and Italy, the evidence is less clear cut. This calls for modesty in interpreting bond yield models and for cautiousness when using them in policymaking.
{"title":"Are European Sovereign Bonds Fairly Priced? The Role of Modeling Uncertainty","authors":"Leo J. de Haan, J. Hessel, Jan Willem van den End","doi":"10.2139/ssrn.2350766","DOIUrl":"https://doi.org/10.2139/ssrn.2350766","url":null,"abstract":"This paper examines the extent to which large swings of sovereign yields in euro area countries during the sovereign debt crisis can be attributed to fundamentals. We focus on the inherent uncertainty in bond yield models, which is often overlooked in the literature. We show that the outcomes are strongly affected by modeling choices with regard to i) the confidence bands for the model prediction, ii) the assumption whether the model coefficients are similar across countries or not, iii) the sample selection, iv) the inclusion of financial variables and v) the choice of time-varying coefficients. These choices affect the explanatory power of macro fundamentals and the extent of mispricing. We find substantial misalignment compared to fundamentals for Greek yields, in most specifications also for Portugal and Ireland, but for the other EMU countries, including Spain and Italy, the evidence is less clear cut. This calls for modesty in interpreting bond yield models and for cautiousness when using them in policymaking.","PeriodicalId":106740,"journal":{"name":"ERN: Other Econometrics: Econometric Model Construction","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126221510","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：