Skip to main content

Mathematical Statistics I · Sufficiency, completeness, and exponential families

For a family of densities or mass functions with respect to one fixed dominating…

Problem

Mathematical Statistics I practice problem

For a family of densities or mass functions with respect to one fixed dominating measure, the factorization theorem says that TT is sufficient if the joint density has the form gθ(T(x))h(x)g_\theta(T(x))h(x), with hh independent of θ\theta. In the usual dominated models here the converse also holds. All support restrictions must be included in that density.

Independent counts XiX_i have Poisson means λti\lambda t_i, where the exposures ti>0t_i>0 are known and λ>0\lambda >0 is unknown. Use factorization to establish sufficiency of K=∑iXiK=\sum_iX_i, and verify the conclusion by finding the conditional distribution of the count vector given KK.

Now suppose the exposures are also unknown and are unrestricted positive parameters. For two counts, show that their total is no longer sufficient for the full parameter vector by examining the conditional probability of (1,0)(1,0) given total 1.

Hint

Hint

Separate factors involving λ\lambda from factors involving only data and known exposures.

Check your work

Work the problem yourself first. Then open it in Training to check your answer and read the full worked solution.

The answer check and full solution for this problem come with ProofAnvil Practice membership ($19 USD monthly). See membership. Or start with the free Mathematical Statistics I sample problem: Try the free sample problem.

More Mathematical Statistics I practice problems