On improved accelerated sequential estimation of the mean of an inverse Gaussian distribution

This paper deals with developing an improved accelerated sequential procedure to estimate the unknown mean mu of an inverse Gaussian distribution, when the scale parameter lambda also remains unknown. The problems of minimum risk and bounded risk point estimation are handled. Consideration is given to a weighted squared-error loss function. Our aim is to control the associated risk functions and obtain the second-order asymptotics as well. Further, we establish the superiority of this improved accelerated sequential sampling design over the Hall's accelerated sequential procedure in estimating an inverse Gaussian mean. Appropriate simulations and real data examples are also provided in support of the encouraging performance of our proposed methodology.