An improvement of a comparison of experiments in statistical decision problems with fuzzy utilities

We present a criterion to compare random experiments in the framework of a single-stage decision problem with fuzzy-valued consequences. This criterion is based on a model introduced by Gil and Lopez-Diaz (1996), and it avoids most of the theoretical and practical limitations of a criterion previously stated by Gil and Jain (1992). Some examples are finally included, to illustrate the study developed in the paper and point out the advantages of the improved method