Hurdle模型及其在居民就诊影响因素中的应用

Hurdle Model and its Application in Hospitalizing Factors of Residents

目的阐明Hurdle模型原理及其在计数资料中的应用。方法利用logit-Poisson Hurdle模型分析两周内居民就诊次数的影响因素。结果 Hurdle模型logistic回归部分结果表明,性别、年龄和经济收入是决定居民是否去医院就诊的主要因素,零截尾Poisson部分结果表明两周内患病次数、由疾病而导致活动天数减少是影响两周内居民就诊次数的主要因素。结论 Hurdle模型是处理零频数过多计数资料一种有效可行的方法 ,其参数估计准确,分析结果切合实际、解释合理。

Objective To explore the application of Hurdle model in Health Service Utilization.Methods Analyse the impacting factors about the number of residents＇ treatment within two weeks applying logit-Poisson Hurdle model.Results The part of logistic revealed gender,age and income of the residents become the factors that deciding whether or not to treatment.And the part of zero-truncated Poisson indicated illness（number of illness in past 2 weeks） and actdays（number of days of reduced activity in past 2 weeks due to illness or injury） were related with the number of visit doctor in past 2 weeks.Conclusion Hurdle model was a feasible and effective method to deal with the count data with excess zeros,its parameter estimation was accurate,the analysis result was in line with reality and easy to explain.