目的 评价北京市居民自报健康调查量表的信度效度,为在北京开展自报健康调查奠定基础.方法 采用多阶段分层抽样的方法对北京市居民进行抽样,通过问卷调查的方法进行现场调查,通过分半信度、克朗巴赫α系数、因子分析、Q型聚类分析等方法对指标体系的信度和效度进行评价.结果 此次调查回收有效问卷4076份.量表的分半信度为0.868,克朗巴赫系数α为0.922,提示具有较好的信度.主成分因子分析和验证性因子分析结果显示,除视力维度和听力维度上的各一个指标的标准化因子载荷较低外,其他指标与相关维度的标准化因子负荷均大于0.6,提示具有较好的结构效度.Q型聚类将样本分为2类,通过x2检验分析,发现各个指标在各组间的差异均有统计学意义(P＜0.01),提示具有较好的区分效度.结论 北京市居民自报健康调查量表的指标体系具有较好的信度和效度,是评估北京市居民自报健康状况的科学有效的工具.%Objective To evaluate reliability and validity of self-reported health scale for Beijing residents,and provide basic evidence for further study in Beijing.Methods A multi-stage stratified sampling method was carried out to select sample population in Beijing.The questionnaire survey was used to collect the information of self-reported health status,and the answers were scored.The Cronbach'sc coefficient,split-half reliability,confirmatory factor analysis and cluster analysis methods were used to assess the reliability and validity of the index system.Results A total of 4076 valid questionnaires were returned.The Cronbach'sc coefficient was 0.922 and the split-half reliability was 0.868,indicating a good reliability.The factor analysis with principal components and confirmatory factor analysis showed that all standardized regression coefficients,except 2 indexes in vision dimension and hearing dimension,were ＞ 0.6,indicating a good construct validity.The significant differences were observed between the groups of being clustered by Q cluster analysis method (P ＜ 0.01),indicating a good discriminant validity.Conclusion The index system of self-reported health scale had a good reliability and validity,and it should be a good tool to evaluate the levels of self-reported health status in Beijing.
展开▼
