Virtually all existing continuous-time, single-factor term structure models are based on a short rate process that has a linear drift function. However, there is no strong a priori argument in favor of linearity, and Stanton (1997) and Ait-Sahalia (1996) employ nonparametric estimation techniques to conclude that the drift function of the short rate contains important nonlinearities. Comparatively little is known about the finite-sample properties of these estimators, particularly when they are applied to frequent sampling of a very persistent process, like short term interest rates. In this paper, we apply these estimators to simulated sample paths of a square-root diffusion. Although the drift function is linear, both estimators suggest nonlinearities of the type and magnitude reported in by Stanton (1997) and Ait-Sahalia (1996). These results, along with the results of a simple GMM estimation procedure applied to the Stanton and Ait-Sahalia data sets, imply that nonlinearity of the short rate drift is not a robust stylized fact.

Viewing The Paper

1) The Economics Working Paper Archive at Washington University (EconWPA)

This paper is posted on the Economics Working Paper Archive (EconWPA) at Washington University. The paper is listed under the "Finance" section paper #9808005. The archive lists an abstract of the paper along with files of the paper that can be viewed and printed. The papers are posted in Adobe Acrobat (*.pdf) format.

Click here to access the EconWPA holding of this paper.

2) PDF Format

Click here to access the *.pdf version of the paper directly....OFOR9807.pdf