| 引用本文： |
-
陈淑兰,闫莉.基于次序Logistic模型的广西大学生消费水平影响因素分析[J].广西科学院学报,2011,27(3):186-189. [点击复制]
- CHEN Shu-lan,YAN Li.Analysis on Consumption Influence Factors of Students from Guangxi University based on Order Logistic Regression Model[J].Journal of Guangxi Academy of Sciences,2011,27(3):186-189. [点击复制]
|
|
| 摘要: |
| 采取随机抽样的调查方法对广西898名在校大学生月均消费水平进行调查,并用次序Logistic模型对调查结果进行分析.结果,以户籍、饮食支出、服饰化妆、抽烟喝酒、娱乐消费、恋爱、话费、兼职收入及家庭收入等因素建立的模型,回归系数的显著性概率都小0.05,通过了Wald检验,且OR值均大于1.表明Logistic模型对上述因素的分析具有显著的统计意义,即影响大学生月均消费的主要因素即为上述9个,而且在其他因素相同情况下,各项消费支出越高,其月均消费就越高,各项收入越高,其月均消费也越高.建议企业从这9个方面制定相应的有效营销策略来开发大学生消费市场. |
| 关键词: 次序Logistic回归 消费水平 影响因素 检验 |
| DOI： |
| 投稿时间：2011-03-01 |
| 基金项目:国家自然科学基金项目(11061002);广西自然科学基金项目(0832108)资助 |
|
| Analysis on Consumption Influence Factors of Students from Guangxi University based on Order Logistic Regression Model |
|
CHEN Shu-lan, YAN Li
|
| (School of Mathematics and Information Science, Guangxi University, Nanning, Guangxi, 530004, China) |
| Abstract: |
| In this article,random sampling method is adopted to investigate the monthly average consumption of students in Guangxi University and about 900 students are randomly sampled.The results from consumption surveys of college students are statistically analyzed by order Logistic model.A reasonable mathematical model is established on the basis of some specific factors.The probability of the significant regression coefficients are all less than 0.05 and pass the Wald test with OR value over 1,which indicates that the model is obviously statistical significance.Therefore,the investigated factors including census register,diet expenditure,dress and make up,smoking and drinking,entertainment,love affair,telephone charges,part time income and family income are main factors that affect the monthly average consumption of students.With the similar other indexes,the higher consumption in these 9 key factors will increase the monthly average consumption.Based on these results,some advises for enterprise developing corresponding strategies for college students market are proposed. |
| Key words: order Logistic regression consumption level influence factors testing |
