On the uniqueness of the maximum likelihood estimator in truncated regression models
这篇短文证明了截断正态回归模型的对数似然函数虽非全局凹，但若存在最大值则唯一，因为海森矩阵在似然方程解处半负定，排除了鞍点和局部极小，不可能有两个以上局部极大。
In this short note it is demonstrated that although the log-likelihood function for the truncated normal regression model may not be globally concave, it will possess a unique maximum if one exists. This is because the hessian matrix is negative semi-definite when evaluated at any possible solution to the likelihood equations. Since this rules out any saddle points or local minima, more than two local maxima occuring is impossible.