论文部分内容阅读
目的探讨伴有协变量的潜在类别模型在两分类资料聚类分析中的应用。方法利用伴有协变量的潜在类别模型对南京市鼓楼区建围产期保健小卡的3 739例孕妇的出生缺陷预防知识调查问卷进行聚类分析。结果将孕妇的出生缺陷预防知识知晓率分成高、中、低3个类别,分别有2 093人(55.98%)、1 431人(38.27%)与215人(5.75%)。15个条目的因子载荷介于0.0857到0.5131之间,不同教育程度、不同职业及不同家庭人均月收入的知晓率在3个类所占比重的差异较大。结论潜在类别模型可用于出生缺陷预防知识知晓率的聚类分析,考虑教育程度、职业及家庭人均月收入为协变量是有必要的。
Objective To explore the application of potential category model with covariate in two-category data clustering analysis. Methods A covariate latent category model was used to cluster the questionnaire of 3 739 pregnant women with prenatal diagnosis of prenatal birth defects in Jianlou District, Nanjing. Results The knowledge of prevention of birth defects among pregnant women was divided into three categories: high, medium and low, with 2 093 (55.98%), 1 431 (38.27%) and 215 (5.75%) respectively. The load factor of 15 items ranged from 0.0857 to 0.5131. There was a big difference in the proportion of three classes in the awareness rate of monthly income among different education levels, different occupations and different families. Conclusions The latent category model can be used to cluster knowledge of prevention knowledge of birth defects. It is necessary to consider the level of education, monthly income of occupation and per capita family as covariates.