Skip to main content
. 2015 Sep 10;6:1342. doi: 10.3389/fpsyg.2015.01342

Figure 2.

Figure 2

(A) State and action space scenario considered in the Section “Optimal Sample Sizes for Parameter Point Inference.” In this Section we consider the case that the decision maker aims to obtain an optimal sample size under the MEU inferential approach while deriving “classical point parameter estimates” of the true, but unknown, state s* of the SSP. Specifically, as will become clear below, the state space S in Section The Maximal Expected Utility Framework corresponds to the interval [0, 1] and so does the action space A. (B) State and action space scenario considered in the Section “Optimal Sample Sizes for Bayesian Parameter Inference.” In this Section we consider the same state space, but a different action space as compared to the Section “Optimal Sample Sizes for Parameter Point Inference.” Specifically, while the state space again corresponds to the interval [0, 1], the action space now corresponds to the set of probability distributions over the interval [0, 1] and the optimal action to a member of this set. This corresponds to a decision maker that aims to obtain an optimal sample size under the MEU inferential approach while performing “Bayesian inference” about the true, but unknown, state of world.