基于稀疏正则化方法的旅游业增长影响因素分析

Factors Affecting China’s Domestic Tourism Growth Based on Sparse Regularization

通过研究SCAD估计、LASSO估计及MCP估计的原理,结合坐标下降算法,对影响我国旅游业发展的主要因素进行实证分析;并将以上方法与逐步回归和最小二乘估计进行对比。研究结果表明:SCAD和MCP估计选择了更加稀疏的模型;SCAD和MCP模型表明国内生产总值和第三产业增加指数等是影响旅游业增长的主要因素,进而可为今后旅游事业的发展和政策的制定提供参考。

This paper makes an empirical analysis of the main factors affecting the development of China’s tourism industry by studying the principles of SCAD estimation,LASSO estimation and MCP estimation,combining with coordinate descent algorithm to calculate and comparing the above methods with stepwise regression and least square estimation.The results show that the SCAD and MCP estimators choose more sparse models.At the same time,the model shows that the GDP and the increase index of the tertiary industry are the main factors affecting the growth of tourism.Which can provide reference for the development of tourism and the formulation of policies in the future.