學術產出-Proceedings
Article View/Open
Publication Export
-
題名 Uncovering Preference Parameters with Higher-Order Consumption Moments 作者 Kuo, Biing-Shen;Lan, Ching-Yu
郭炳伸貢獻者 國貿系 日期 2006 上傳時間 2-Apr-2015 11:35:31 (UTC+8) 摘要 Despite the importance of estimating structural parameters governing consumption dynamics, such as the elasticity of intertemporal substitution, empirical attempts to un- veil these parameters using a log-linearized version of the Euler equation have produced many puzzling results. Some studies show that the approximation bias may well con- stitute a compelling explanation. Even so, the approximation technique continues to be useful and convenient in estimation of the parameters, because noisy cEmpirical attempts using panel data to unveil preference parameters by a log-linearized version of the Euler equation have produced many buzzling results. Recent studies have shown that the approximation bias may be responsible for these anomalies. Motivated by its potential success in reducing the bias, we investigate the economic significance and empirical relevance of higher-order approximations to the Euler equation with simulation method. The approach mounted has the advantages of easy implementation and being less prone to misspecification. Our simulation results clearly reveal that the approximation bias can be significantly reduced when the higher-order moments are introduced, but at the cost of efficiency loss, the conventional tradeoff between bias reduction and efficiency loss. Our study contributes as well to the selection of the approximation order. With the selection criteria proposed in the paper, we find that the mean-squared errors may be substantially reduced simply by adding a small number of the higherorder moments to the second-order approximated consumption regression. Remarkably, when applying our approach to PSID, ‘reasonable’ preference parameter estimates, as suggested in the literature, can now be produced. onsumption data renders a full-edged GMM estimation unreliable. Motivated by its potential success in reducing the bias, we investigate the economic signicance and empirical relevance of higher-order approximations to the Euler equation with simulation methodology. The higher-order approximations suggest a linear relationship between expected consump- tion growth and its higher-order moments. Our simulation results clearly reveal that the approximation bias can be signican tly reduced when the higher-order moments are introduced into estimation, but at the cost of eciency loss. It therefore documents a clear tradeo between approximation bias reduction and eciency loss in the con- sumption growth regression when higher-order approximations to the Euler equation is considered. A question of immediate practical interest arises How many higher-order terms are needed?" The second part of our Monte-Carlo studies then deals with this issue. We judge whether a particular consumption moment should be included in the regression by the criterion of mean squared errors (MSE) that accounts for a trade-o between estimation bias and eciency loss. The included moments leading to smaller MSE are regarded as ones to be needed. We also investigate the usefulness of the model and/or moment selection criteria in providing guidance in selecting the approximation order. We nd that improvements over the second-order approximated Euler equation can always be achieved simply by allowing for the higher-order moments in the consump- tion regression, with the approximation order selected by these criteria. 關聯 中央研究院經濟研究所 每週研討會 資料類型 conference dc.contributor 國貿系 dc.creator (作者) Kuo, Biing-Shen;Lan, Ching-Yu dc.creator (作者) 郭炳伸 zh_TW dc.date (日期) 2006 dc.date.accessioned 2-Apr-2015 11:35:31 (UTC+8) - dc.date.available 2-Apr-2015 11:35:31 (UTC+8) - dc.date.issued (上傳時間) 2-Apr-2015 11:35:31 (UTC+8) - dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/74336 - dc.description.abstract (摘要) Despite the importance of estimating structural parameters governing consumption dynamics, such as the elasticity of intertemporal substitution, empirical attempts to un- veil these parameters using a log-linearized version of the Euler equation have produced many puzzling results. Some studies show that the approximation bias may well con- stitute a compelling explanation. Even so, the approximation technique continues to be useful and convenient in estimation of the parameters, because noisy cEmpirical attempts using panel data to unveil preference parameters by a log-linearized version of the Euler equation have produced many buzzling results. Recent studies have shown that the approximation bias may be responsible for these anomalies. Motivated by its potential success in reducing the bias, we investigate the economic significance and empirical relevance of higher-order approximations to the Euler equation with simulation method. The approach mounted has the advantages of easy implementation and being less prone to misspecification. Our simulation results clearly reveal that the approximation bias can be significantly reduced when the higher-order moments are introduced, but at the cost of efficiency loss, the conventional tradeoff between bias reduction and efficiency loss. Our study contributes as well to the selection of the approximation order. With the selection criteria proposed in the paper, we find that the mean-squared errors may be substantially reduced simply by adding a small number of the higherorder moments to the second-order approximated consumption regression. Remarkably, when applying our approach to PSID, ‘reasonable’ preference parameter estimates, as suggested in the literature, can now be produced. onsumption data renders a full-edged GMM estimation unreliable. Motivated by its potential success in reducing the bias, we investigate the economic signicance and empirical relevance of higher-order approximations to the Euler equation with simulation methodology. The higher-order approximations suggest a linear relationship between expected consump- tion growth and its higher-order moments. Our simulation results clearly reveal that the approximation bias can be signican tly reduced when the higher-order moments are introduced into estimation, but at the cost of eciency loss. It therefore documents a clear tradeo between approximation bias reduction and eciency loss in the con- sumption growth regression when higher-order approximations to the Euler equation is considered. A question of immediate practical interest arises How many higher-order terms are needed?" The second part of our Monte-Carlo studies then deals with this issue. We judge whether a particular consumption moment should be included in the regression by the criterion of mean squared errors (MSE) that accounts for a trade-o between estimation bias and eciency loss. The included moments leading to smaller MSE are regarded as ones to be needed. We also investigate the usefulness of the model and/or moment selection criteria in providing guidance in selecting the approximation order. We nd that improvements over the second-order approximated Euler equation can always be achieved simply by allowing for the higher-order moments in the consump- tion regression, with the approximation order selected by these criteria. dc.format.extent 286097 bytes - dc.format.mimetype application/pdf - dc.relation (關聯) 中央研究院經濟研究所 每週研討會 dc.title (題名) Uncovering Preference Parameters with Higher-Order Consumption Moments dc.type (資料類型) conference en
