验证性因子分析在临床医学科技成果评价指标体系研究中的应用  

Application of confirmatory factor analysis in studying the achievements of index system in clinical sciences and technologies

作　　者：鲁菁[1,2] 李海燕[3] 周映雪[3] 陈立章[1] 

机构地区：[1]中南大学公共卫生学院,长沙410078 [2]中华医学会北京分会 [3]南方医科大学

出　　处：《中华流行病学杂志》2011年第12期1285-1288,共4页Chinese Journal of Epidemiology

基　　金：广东省科技计划项目（2008A040302003）

摘　　要：探讨验证性因子分析在科技成果评价指标体系中的作用。以临床医学科技成果评价指标体系为工具，收集实测数据，利用SPSS和AMOS软件分析，通过验证性因子分析评价指标体系的结构效度并确立各指标的权重。结果表明二阶验证性因子模型经检验尸值均〉0．05，说明实测数据与指标体系的构建理论和设想相吻合，拟合指数等拟合优度指标均〉0．90，说明模型拟合效果佳。基于验证性因子分析的因子载荷确立了各指标的权重，其结果与Delphi法所确立的权重高度一致。验证性因子分析可以客观地分析各级指标之间的从属关系，可推广应用于指标体系的结构效度评价以及权重的确立。To explore the role of confirmatory factor analysis in checking the construct validity of index system in clinical sciences and technologies and to determine the weighting of each index. Data were collected based on the achievements regarding the index system of sciences, technologies and analyzed by softwares SPSS and AMOS. Confirmatory factor analysis was performed to assess the construct validity and to identify the weighting. The P values for testing the two-order confirmatory factor models were bigger than 0.05, indicating that the actual data were in agreement with theory in designing the index system. Statistics on the goodness fit index （GFI） such as GFI were bigger than 0.90, indicating that they were satisfactory. Weightings for each index were identified based on factor loading of confirmatory factor analysis, showing that they were highly correlated with that from the Delphi method. Confirmatory factor analysis appeared to be an appropriate method in analyzing the associations among the index variables, and could be widely used to assess the construct validity of index system and identifing the weightings.

关 键 词：验证因子分析 结构效度 评价指标体系 

分 类 号：R-5[医药卫生]