摘要
目的探讨零膨胀负二项回归模型在居民患有共存疾病及其影响因素研究中的应用。方法分别用Poisson分布、负二项分布和零膨胀模型来拟合居民共存疾病数量并分析聚集性,筛选出共存疾病的主要影响因素。结果拟合分布的结果显示,共存疾病数量不符合Poisson分布(χ~2=196. 419,P <0. 001),符合负二项分布(χ~2=6. 677,P=0. 154);聚集指数K=1. 779,过离散检验统计量O=15. 18> 1. 96,所以资料存在聚集性。零膨胀检验统计量Vuong=6. 58,P <0. 001,零膨胀模型要优于Poisson或负二项模型。零膨胀负二项回归分析显示:在负二项部分得出,年龄越大、有高强度运动、焦虑程度越高、体质指数越高、糖化血红蛋白(hemoglobin A1c,Hb A1c)水平越高、有糖尿病家族史、有高血压史、高收缩压和高水平胆固醇的居民发生共存疾病的数量会增加;在Logit部分得出,年龄越大、焦虑程度越高、体质指数越高、甘油三酯水平越高、空腹血糖(fasting blood glucose,FPG)越高、有高血压家族史和高收缩压的居民发生慢性病的风险较大。结论居民患共存疾病有聚集性和零计数过多的特点,零膨胀负二项回归模型在拟合具有该类特点的数据中优势明显。
Objective To study the application of zero-inflated negative binomial regression model in the residents＇ multimorbidity and its impacting factors. Methods Poisson distribution, negative binomial distribution and zeroinflated model were used to fit the number of muhimorbidity and the aggregation was analyzed, then the main factors were screened out in multimorbidity. Results The number of muhimorbidity did not accord with Poisson distribution （X2 = 196. 419, P 〈 0. 001 ） and meet the negative binomial distribution （X2 = 6. 677, P = 0. 154） ; the aggregation index K = 1. 779, over-dispersion test 0 = 15.18 〉 1.96, so the data was clustered. Zero expansion test Vuong -6. 58, P 〈0. 001, zero-inflate model was better than Poisson or negative binomial model. The negative binomial part of the results suggest that- the number of muhimorbidity will increase, when the residents had risk factors including the older, high intensity exercise, the higher the degree of anxiety, the higher the body mass index, the higher the hemoglobin Alc（HbAlc） level, a family history of diabetes, high blood pressure history, high systolic blood pressure and high levels of cholesterol; In the Logit part of the results： residents had a higher risk of developing chronie diseases, who had risk factors which included the older, the higher the degree of anxiety, the higher the body mass index, the higher the level of triglycerides, the higher the fasting blood glucose （ FPG）, the family history of hypertension and high systolic blood pressure. Conclusion Multimorbidity is characterized by aggregation and zero-inflated count. Zero-inflated negative binomial regression model has obvious advantages in fitting the data with such characteristics.
作者
朱高培
朱乐乐
孟马承
吴学森
ZHU Gao-pei;ZHU Le-le;MENG Ma-cheng;WU Xue-sen(Department of Epidemiology and Biostatistics,School of Public Health,Bengbu Medical College,Bengbu 233030,China)
出处
《中华疾病控制杂志》
CAS
CSCD
北大核心
2018年第10期1063-1066,共4页
Chinese Journal of Disease Control & Prevention
基金
国家自然科学基金(81373100)
蚌埠医学院研究生创新计划项目(Byycx1658)
关键词
共存疾病
聚集性
零膨胀负二项回归模型
Muhimorbidity
Aggregation
Zero-inflated negative binomial regression model
