77. Inverse Gaussian distribution:" Let Xl"'" X; be a sample from the inverse Gaussian distribution I(p., T), both parameters unknown. (i) There exists a UMP unbiased test of p. P.o against p. > P.o, which rejects when X> C[L(X; + 1/X;»), and a corresponding UMP unbiased "For additional information concerning inference in inverse Gaussian distributions, see Folks and Chhikara (1978).

test of J.L = J.Lo against J.L * J.Lo· [The conditional distribution needed to carry out this test is given by Chhikara and Folks (1976).] (ii) There exist UMP unbiased tests of H : T = TO against both one- and two-sided