贝叶斯Logistic回归模型在中老年人心脏病影响因素分析中的应用

Application of Bayesian logistic regression model in the analysis of influencing factors of heart disease in middle-aged and older adults

目的探讨贝叶斯Logistic回归模型在心脏病影响因素分析研究中的应用价值。方法数据资料来自2015年中国健康与养老追踪调查中的525例调查对象。利用OpenBUGS软件分别拟合了贝叶斯随机效应和固定效应的Logistic回归模型,并在两种模型中估计各影响因素与因变量关系的优势比(OR)及95%可信区间(95%CI)。结果贝叶斯随机效应和固定效应的Logistic回归模型分析结果均显示,性别、高血压和糖尿病是心脏病患病率的影响因素。两个模型的收敛效果均较好,参数估计结果也相差较小,但随机效应模型的拟合效果略差于固定效应模型(随机效应模型:DIC=156.6,pD=11.96;固定效应模型:DIC=155.8,pD=7.79)。结论在贝叶斯Logistic回归模型中引入随机效应参数需根据具体情况而定,否则反而可能会降低模型的拟合效果。

Objective To explore the application of Bayesian random-effects logistic regression model in the study of factors in-fluencing heart disease.Methods The data came from 525 survey subjects in the China Health and Retirement Longitudinal Study con-ducted in 2015.Bayesian logistic regression models with random and fixed effects were fitted using OpenBUGS software to estimate the odds ratio(OR)and 95%confidence interval(95%CI)of the relationship between each influential factor and the dependent variable.Results The results of both Bayesian logistic regression models with random and fixed effects showed statistically significant effects of gender,hypertension,and diabetes on heart disease in the respondents.The convergence of both models was good,and the difference in parameter estimates was small,but the goodness of fit of the random effects model was slightly worse than that of the fixed effects model(random effects model:DIC=156.6,pD=11.96;fixed effects model:DIC=155.8,pD=7.79).Conclusion In the Bayesian Logistic regression model,the introduction of random effect parameters should be determined based on specific circumstances;otherwise,it may reduce the model’sfit effect.