solidot新版网站常见问题,请点击这里查看。

Forecast dominance testing via sign randomization. (arXiv:1707.03035v2 [math.ST] UPDATED)

来源于:arXiv
We propose randomization tests of whether forecast 1 outperforms forecast 2 across a class of scoring functions. This hypothesis is of applied interest: While the prediction context often prescribes a certain class of scoring functions, it is typically hard to motivate a specific choice on statistical or substantive grounds. We investigate the asymptotic behavior of the test statistics under mild conditions, avoiding the need to assume particular dynamic properties of forecasts and realizations. Properties of one-sided tests depend on a one-sided variant of Anderson's inequality, which we state as a conjecture of independent interest. Simulation experiments and data examples indicate that the tests have good size and power properties in practically relevant situations. 查看全文>>