作者: Bonsoo Koo , Oliver B. Linton
DOI: 10.2139/SSRN.1673535
关键词:
摘要: This paper proposes a class of locally stationary diffusion processes. The model has time varying but linear drift and volatility coefficient that is allowed to vary over space. We propose estimators all the unknown quantities based on long span data. Our estimation method makes use local stationarity. establish asymptotic theory for proposed as increases. apply this real financial data illustrate validity our model. Finally, we present simulation study provide finitesample performance estimators.