Abstract: Time-domain state-domain methods are common approaches in modern financial analysis. Economic conditions vary time, drift function depends on time and price level for a given state variable. In this paper, to consistently estimate the bivariate drift function, our purpose a new dynamic integrated estimator by combing time-and state-domain methods for estimating drift function. And we establish its asymptotic properties and illustrates it outperforms some old ones by simulations.

Key words: time-domain, state-domain, integrated estimator, drift function