A Composite Generalized Cross-Entropy Formulation in Small Samples Estimation
提出一种基于最大熵的估计方法，结合小样本子群体和大样本总体的信息，推导出复合交叉熵估计量，并用于估计意大利家庭子群体的支出份额。
This article introduces a maximum entropy-based estimation methodology that can be used both to represent the uncertainty of a partial-incomplete economic data generation process and to consider the direct influence of learning from repeated samples. Then, a composite cross-entropy estimator, incorporating information from a subpopulation based on a small sample and from a population with a larger sample size, is derived. The proposed estimator is employed to estimate the local area expenditure shares of a sub population of Italian households using a system of censored demand equations.