Abstract

In behavioral science, there are many studies of factor analysis for time series data. These studies assumed a discrete-time stochastic process model. Since the development of measuring devices enables us to obtain high-frequency data, factor analysis based on high-frequency data has become important. In financial econometrics, principal component analysis can estimate the factor model for high-frequency data. However, this method is not appropriate for a low-dimensional model. In this paper, we consider exploratory factor analysis for diffusion processes based on high-frequency data. Unlike principal component analysis, our method works well for a low-dimensional model.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call