The Decision to Establish a Foreign Bank Branch or Subsidiary: An Application of Binary Classification Procedures
利用外国银行在日本和加利福尼亚的外商直接投资数据，运用线性判别分析和最大似然逻辑分析，研究母行国际经验如何影响其选择设立分行还是子公司。
This paper has two purposes. First, we model a key decision for inter? national banks using data on the foreign direct investment (FDI) behavior of foreign banks in Japan and California. Second, we examine the utility of linear discriminant analysis and maximum likelihood logit analysis as statistical techniques for relating a qualitative dependent variable to a vector of inde? pendent variables. We apply these techniques to the decision by parent banks as to whether or not to have a subsidiary (branch) in California (Japan). We treat the deci? sion as a binary choice based on a consideration of various relevant factors. The population for each of the countries consists of those foreign (to the host country) banks that already have a presence in the country. The research ques? tion then becomes: given that a foreign bank is in the country, does the extent of the parent bank's experience internationally and in the host country affect the probability that it will deepen its presence? The choice of statis? tical tools by which to examine this question gives rise to our methodological concerns.