论文部分内容阅读
本文提出应以动态和变化的观点去认识疾病发生的统计分布规律。单一参数模型已不能满足实际需要．为此，本文探讨了几种生物学意义较为明朗的复合分布及其应用。包括：负二项分布（又称Ｔ－Ｐｏｉｓｓｏｎ分布），β二项分布，ＰｏｉｓｓｏｎＰｏｉｓｓｏｎ分布，Ｐｏｉｓｓｏｎ一二项分布，混合Ｐｏｉｓｓｏｎ分布，并首次提出带协变量的分布和时依Ｐｏｉｓｓｏｎ分布的概念，从应用效果来看是满意的．这为疾病监测方法的建立、病因学研究，尤其是聚集性疾病的研究提供一理论依据．
This paper proposes that the statistical distribution of disease occurrence should be understood from the perspective of dynamics and change. Single parameter model can not meet the actual needs. For this reason, this article explores several compound distributions with clear biological implications and their applications. Including: negative binomial distribution (also known as T-Poisson distribution), β binomial distribution, PoissonPoisson distribution, Poisson-1 binomial distribution, mixed Poisson distribution, and for the first time put forward the concept of distribution and time-dependent Poisson distribution with covariates. The application effect is satisfactory. This provides a theoretical basis for the establishment of disease surveillance methods, etiological studies, especially for the study of aggregated diseases.