The Cramér-Von Mises goodness-of-fit statistic, also known as the L2-star discrepancy, is the optimality criterion for an experimental design for the location model with misspecification. This connection between goodness-of-fit statistics, discrepancies and experimental designs is shown to hold in greater generality. © 1998 Elsevier Science B.V.
Hickernell, F. J. (1999). Goodness-of-fit statistics, discrepancies and robust designs. Statistics and Probability Letters, 44(1), 73–78. https://doi.org/10.1016/S0167-7152(98)00293-4