DECONVOLUTING PREFERENCES AND ERRORS: A MODEL FOR BINOMIAL PANEL DATA
针对陈述选择实验中观测到的二项面板数据，提出一种筛极大似然估计方法，在弱假设下一致估计不可观测变量分布和未知参数。
In many stated choice experiments researchers observe the random variables V t , X t , and Y t = 1{ U + δ ⊤ X t + ε t < V t }, t ≤ T , where δ is an unknown parameter and U and ε t are unobservable random variables. We show that under weak assumptions the distributions of U and ε t and also the unknown parameter δ can be consistently estimated using a sieved maximum likelihood estimation procedure.