摘要
目的 编制大学生安全感量表,调查在校大学生安全感的主观感受,根据感受的倾向性和特征,进一步分析导致不安全感的主客体因素.方法 利用自行编制的大学生安全感调查量表,采用分层整群随机抽样的方法,在预调查的基础上对某市四所高校500名在校大学生进行调查,运用SPSS17.0、AHP与SAS9.1统计软件对数据进行统计分析.结果 量表的Cronbach＇s系数为0.629;大学生安全感的四个维度及总安全感均处于中等偏上水平,被试大学生的总体安全感得分在年级、性别和是否单亲方面的差异有统计学意义（均P＜0.05）,自我安全感在年级、性别方面差异显著（P＜0.01,P＜0.05）,人际安全感在性别和是否单亲家庭方面的差异有统计学意义（均P＜0.05）,确定控制感和家庭安全感在这些人口学变量方面差异无统计学意义.多因素分析结果显示,决策树模型优于Logistic回归模型（错误分类率低）,确定影响大学生安全感的主要因素有性别、年级、家庭人均年收入和是否独生子女；且大学生安全感的各维度之间存在显著正相关,各维度安全感的水平均可能影响其他安全感的状况.结论 量表具有较好的信度与效度,可用于大学生安全感调查；调查人群的总体安全感处于中等偏上水平,性别、年级、人均年收入与是否独生子女是影响大学生不安全感的潜在因素.
Objective To develop the security scale of college students＇ sense to investigate college students＇ subjective feeling of security. According to the characteristie, s of the feeling tendentiousness to analysis the subject and object tactors influencing the insecurity of college students.Methods The security scale of college students ＇ sense compiled was administrated to 500 college student randomly stratified cluster sampling fi＇om four u- niversities in Yantai,then description and analysis were analyzed by SPSS17.0, AHP and SAS9.1 to statistical.Re- suits Through the scale of exploratory factor analysis,the Cronbaeh＇ s of the scale was 0.629. College students in tbur dimensions of security and total security were in above-average levels, college students＂ total score of security is significanee of difference in grade, gender and whether come from the single parent（ all P〈0.05 ） ;Sell＂ security was significance of difterence in the grade and the gender（P〈0.01 and P〈0.05） ; and intml）ersonal security in gender and whether come from the single parent had significance difference（P〈0.05） ;Determine control and family securi- ty in these demographic, variable aspects had no significant dirt）fences. Multivariate factors analysis results showed that the decision tree model was better than the logistic model（ the miselassification rate of the model was lower than the decision tree model）. The main factors articling the university students＂ security were gender,grade, the average income and whether they were the only children. The misclassifieation rate of the decision tree model was lower than the model of logistic.College students＂ sense of dimensions are significant with positive correlation, the dimension of the security level may affect other seeurity of the situation. Conclusion The security scale of college students＇ sense has good reliability and validity and can be used in the study of college security. The tactor analy- sis determines it can be used multiple factors analysis. The survey shows that the overall security of the crowd＇ s is over the average level. The gender,grade, annual per-capita income and whether the one-chihl are the potential factors that aft）el college students＇ insecurity.
出处
《中华行为医学与脑科学杂志》
CAS
CSCD
北大核心
2014年第3期264-267,共4页
Chinese Journal of Behavioral Medicine and Brain Science
基金
国家统计科研一般项目（2012LY074）子课题
滨州医学院大学生科技创新项目（BY2010DKCX85）
关键词
安全感
大学生
影响因素
决策树
LOGISTIC回归
Security sense
College students
Influencing factors
Decision tree
Logistic regres-sion
