摘要：This paper deals with the density for a class of estimators _??_ c 1 c 2 ( c 1, c 2≥0) in Gaussian AR (1) process. Here _??_ c 1 c 2 includes various estimators if the constants c 1 and c 2 are specified appropriately. Applying the saddlepoint method to the general formula by Geary [5], the density of _??_ c 1 c 2 is approximated. Although Phillips [14] pointed out that the saddlepoint density is undefined in a substantial part of the tails, we elucidate that the resulting approximation is always defined if c 1 and c 2 are appropriately chosen. Some numerical comparisons are made among the Edgeworth approximation, the saddlepoint approximation, and the exact distribution for _??_1/2, 1/2. We also approximate the density for the mean corrected estmator _??_ c 1 c 2.
