检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]安徽医科大学流行病与卫生统计系,合肥230032 [2]安徽医科大学营养与食品卫生系
出 处:《中国学校卫生》2003年第6期600-601,共2页Chinese Journal of School Health
基 金:达能膳食营养研究与宣教基金(编号 :2 0 0 0 6 )
摘 要:目的 采用主成分分析法综合评价不同年龄、性别儿童的生长发育状况 ,探讨科学的评价方法。方法 分层整群随机抽取合肥市 8所幼儿园 1 86 3名儿童 ,测量其身高、体重、坐高、头围、胸围、上臂围、三头肌、肩胛下皮褶厚度等形态学指标 ,采用主成分分析法综合评价。结果 前 2个主成分Z1和Z2 累积贡献率达到 89.1 % ,被确定为重要主成分 ,建立主成分函数表达式 ,分析主成分与原始变量之间的关系。通过Z1,Z2 分别与年龄、性别作单变量方差分析发现 :随着年龄的增长 ,Z1得分不断增加 ,说明儿童正处于生长发育的上升时期 ,而Z2 得分变化幅度较小 ,说明体脂含量相对恒定 ,且二者在性别间差异皆存在统计学意义 (P <0 .0 5)。结论 运用主成分分析可以消除原始变量间的信息重叠 ,合理。ObjectiveTo evaluate synthetically the develop me nt and nutritional status of children in different age and gender groups by usin g principle component analysis, and to establish scientific evaluation method. MethodsApproximately 1 863 children were randomly selected fro m eight kindergartens in Hefei by stratified and cluster sampling.The children' s morphological indexes were measured, which included body height,body weight, sitting height,head circumference,chest circumference,upper arm circumference ,triceps skinfold and subscapular skinfold.The principle component analysis wa s applied to determine the key principal components.ResultsWh en 89.1% of cumulative variance proportion was regarded as limit, two principal components and their function equations were given. The relationship between pri ncipal components and their original variables was analyzed.One-way variance a nalysis was used to test the relations of first two principle components to age and sex, it was revealed that change in Z 1 score was greater while change in Z 2 score was smaller with increasing age, indicating development of children w ere i n ascending stage while their body fat content remained at a constant level, age and gender differences were found in Z 1 score and Z 2 score(P<0.05) . ConclusionIt is indicated that the principle component analysi s could not only simplify indices to exclude the overlapping effects of primeval variables, but also could evaluate development status of children reasonably an d synthetically.
分 类 号:R195.1[医药卫生—卫生统计学] R195.2[医药卫生—卫生事业管理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.28