中国创业板上市公司盈利能力的因素分析--基于分位数回归的实证研究

摘要

There are many factors affecting the profitability of listed companies .The impact of various factors on prof-itability may differ under different sub-digit level.Traditional regression model can only describe the mean variable depending on the conditions affected the independent variable;while quantile regression model can be variable de-pending on the conditions based on the independent variables quantile regression , which results in a more accurate-ly description of the effect of independent variable on the dependent variable .This study selects cross-section data from 355 companies listed on GEM before June 30 , 2013 to study the effects of various factors from the perspective of quantile regression under different quantile levels of profitability for the company , and adds the regional dummy variables to study the relationship between location factors and profitability .%影响上市公司盈利能力的因素有很多，不同的分位数水平下各因素对盈利能力的影响可能存在差异。传统的回归模型只能描述因变量的条件均值受自变量的影响，而分位数回归模型能够依据因变量的条件分位数对自变量进行回归，从而更加精确地描述自变量对因变量的影响。选取截至2013年6月30日的355家创业板上市公司的截面数据，从分位数回归的角度研究了不同分位数水平下各因素对公司盈利能力的影响，并且加入了地区虚拟变量，研究了区位因素与盈利能力的关系。