传统的面板数据分析主要是基于条件均值方法进行研究.文章讨论了只含有固定效应的面板数据模型,从理论上提出了两阶段K步差分的分位回归方法,并证明了其大样本性质.同时进行了蒙特卡洛模拟,结果显示该方法在误差非正态时比均值回归方法更有效.最后对我国城镇居民医疗保健消费进行了实证分析,得到了一些有趣的发现,这可以供决策者进行参考. The traditional panel data analysis is mainly based on the conditional mean method.This paper discusses the panel data model with only fixed effects, and theoretically proposes a two-stage fractional regression method of K-step difference, and proves its large sample properties. At the same time, the Monte Carlo simulation results show that this method is more effective than the average regression method when the error is not normal.Finally, this paper empirically analyzes the health care consumption of urban residents in our country and obtains some interesting findings, which can be used by decision makers For reference.