ABSTRACT
This chapter is based on Tanizaki (2000, 2001). In the case where the lagged dependent variables are included in the regression model, it is known that the ordinary least squares estimates (OLSE) are biased in small sample and that bias increases as the number of the irrelevant variables increases. In this chapter, based on the bootstrap methods, an attempt is made to obtain the unbiased estimates in autoregressive and non-Gaussian cases. We introduce the residual-based bootstrap method in this chapter. See Efron and Tibshirani (1993) for the bootstrap methods. Some simulation studies are performed to examine whether the estimation procedure discussed in this chapter works well or not. We obtain the results that it is possible to recover the true parameter values based on OLSE and that the discussed procedure gives us the less biased estimators than OLSE.
