关键词: 非平稳性, 面板数据, 离散选择模型, 显著性检验

Abstract: With the advent of the big data era and the improvement of the statistical system, the macroeconomic and financial field increasingly tend to use large-dimensional panel data to do empirical research and the theory of large-dimensional panel data model has become a research focus in modern econometric theory. This paper studies the limit theory for discrete choice nonstationary panels. The results show that when the true parameter vector of explanatory variables is zero, the maximum likelihood estimator is consistent and has a normal limit distribution. Also the classical Wald statistic is still useful and has a Chi-squared limit distribution.

Key words: Nonstationarity, Panel Data, Discrete Choice Model, Significance Test