[题目] Testing for Structural Changes in Large Dimensional Factor Models via Discrete Fourier Transform

[主讲人] 王霞，中山大学岭南学院

[主持人] 章勇辉，中国人民大学经济学院

[时间] 2019年9月20日16:00

[地点] 明德主楼729会议室

[摘要] We propose a new test for structural changes in large dimensional factor models via a discrete Fourier transform (DFT) approach. If structural changes exist, the conventional principal component analysis will fail to estimate common factors and factor loadings consistently. The estimated residuals will contain information about structural changes. Therefore, we can compare the DFT of the residuals with the null (zero) spectrum implied by no structural change. The proposed test is powerful against both smooth structural changes and abrupt structural breaks with possibly unknown number of breaks and unknown break dates in factor loadings. It can detect a class of local alternatives at the rate T^{-1/2} N^{-1/2}, where T and N are the numbers of time periods and cross-sectional units. As a result, the test is asymptotically more efficient than the existing tests in the factor model literature. Moreover, it is easy to implement and tuning parameter-free. And our test is robust to serial dependence and cross-sectional dependence of unknown form. Monte Carlo studies demonstrate its reasonable size and excellent power in detecting structural changes of unknown types in factor loadings. In an application to Stock and Watson`s (2012) U.S. macroeconomic data, we find significant and robust evidence against time-invariant factor loadings.

[主讲人简介] 王霞，2013年毕业于厦门大学王亚南经济研究院，现为中山大学岭南学院副教授。主要研究兴趣包括：理论计量经济学，时间序列分析，宏观经济与货币政策，曾在Journal of Econometrics、International Economic Review、Econometric Theory、 Journal of Business & Economic Statistics、《经济研究》、《管理科学学报》等国内外核心期刊发表论文20余篇。