讨论了单峰分布的最短置信区间的问题。
The shortest Confidence interval of unimodal distribution is discussed.
这说明在小样本下，研究参数的最短置信区间是必要的。
So it is necessary to research the shortest confidence interval of parameter for small samples.
用传统方法得到的伽玛分布参数的置信区间显然不是最短，因而在这个意义上讲也不是最优的。
The confidence interval of parameter of Gama distribution, obtained by using the traditional method, is obviously not the shortest. So it is not the best one in this sense.
用传统方法得到的两正态分布方差比的置信区间显然不是最短的，因而就此意义而言也不是最佳的。
The traditional method the confidence interval is not the shortest, so it is not the best one in this sence. Obtained the shortest confidence interval in theory.
用传统方法得到的两正态分布方差比的置信区间显然不是最短的，因而就此意义而言也不是最佳的。
The traditional method the confidence interval is not the shortest, so it is not the best one in this sence. Obtained the shortest confidence interval in theory.
应用推荐