An Ancillarity Paradox in the Estimation of Multinomial Probabilities
研究了多项分布中，当样本量n是辅助统计量时，固定样本量下的极小化极大估计量在平方误差损失下不再极小化极大，但在相对平方误差损失下仍然成立。
Let X be a multinomial (n, p) variable, where n is an ancillary statistic. In Section 2, it is shown that the minimax estimator of p for fixed sample size n is not minimax for squared error loss. In Section 3, it is shown that the minimax estimator of p for fixed sample size n is still minimax for relative squared error loss.