Abstract
On the Spectral Distribution of Hayashi's Estimator for High Dimensional Stock Price Process
by
Arnab Chakrabarti
We consider the problem of estimation of integrated covariance for high dimensional financial stock price process. As the stock price data is fundamentally nonsynchronous it is worthwhile to think about Hayashi's method of estimation (Hayashi, Yoshida 2004). The asymptotic results for small dimension is already established by Hayashi and Yoshida (Hayashi, Yoshida 2007). But in high dimensional setup when the dimension p and observation frequency grow in same rate this estimator is no longer a consistent estimator of integrated covariance. In this situation to come to some meaningful inference study of limiting behavior of the empirical spectral distribution (ESD) of high dimensional Hayashi's estimator matrix is a possible way out. In this study we want to get hold of the limiting spectral distribution of Hayashi's estimator by establishing a Marcenko-Pastur type theorem.
Committee
Workshop
Key Dates
Communication
First Conference Link