Is the Short Rate Drift Actually Nonlinear?

摘要

Ait-Sahalia (1996) and Stanton (1997) use nonparametric estimators applied to short-term in test rate data to conclude that the drift function contains impor- tant nonlinearities. We study the finite-sample properties of their estimators by applying them to simulated sample paths of a equare-root diffusion. Although the drift function is linear, both estimators suggest nonlinearities of the type and mag- nitude reported in Alt-Sahalia (1996) and Stanton (1997). Combined with the re- sults of a weighted least squares estimator, this evidence implies that nonlinearity of the short rate drift is not a robust stylized fact.