【主题】Latent Local-to-Unity Models
【报告人】王晓虎（副教授，复旦大学yobo体育全站app下载）
【时间】2022年11月29日 周二 下午14:30-16:00
【地点】腾讯会议，会议ID：423 947 088，密码：757 878
【语言】中文
【摘要】This paper studies a class of state-space models where the state equation is a local-to-unity process. The interest is in the inference of the persistence parameter of the latent process. Large sample theories for the least squares (LS) estimator and an instrumental variable (IV) estimator of the autoregressive (AR) parameter with fitted intercept in the AR representation of the model are developed under two sets of conditions. In the first set of conditions, the error term in the state equation is stationary and fractionally integrated with memory parameter d∈(-0.5,0.5). For the LS estimator, it is shown that both the rate of convergence and the asymptotic distribution crucially depend on d. More importantly, the existence of measurement errors aggravates the downward stochastic bias of the LS estimator when d≤0. In contrast, the measurement errors play no role in the limiting distribution of the IV estimator. In the second set of conditions, the error term in the state equation is strongly mixing. It is explored again that measurement errors affect the limiting distribution of the LS estimator but not that of the IV estimator. Special cases of our models and results in relation to those in the literature are discussed.
【报告人简介】王晓虎，复旦大学yobo体育全站app下载国际金融系副教授。2012年获得新加坡管理大学经济学博士学位。曾工作于香港中文大学经济系，2020年加入复旦大学。主要研究领域为金融计量和实证资产定价。研究成果发表在Journal of Econometrics，Econometrics Journal, Econometric Reviews, Journal of International Money and Finance, Advances in Econometrics, Economics Letters, Econometrics,等学术期刊上。