当前位置:
X-MOL 学术
›
Math. Popul. Stud.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Expectation maximization estimates of the offspring probabilities in a class of multitype branching processes with binary family trees
Mathematical Population Studies ( IF 1.8 ) Pub Date : 2017-10-02 , DOI: 10.1080/08898480.2017.1348723 Nina Daskalova 1
Mathematical Population Studies ( IF 1.8 ) Pub Date : 2017-10-02 , DOI: 10.1080/08898480.2017.1348723 Nina Daskalova 1
Affiliation
ABSTRACT When proliferating cells are counted in several independent colonies at some time points, the maximum likelihood estimates of the parameters of the multitype branching process are obtained trough an expectation maximization algorithm. In the case of an offspring distribution governed by a Markov branching process with binary family trees, this method, relying then on a partial knowledge of the tree, yields the same estimates as those computed with the complete knowledge of the tree.
中文翻译:
一类多类型分支过程中子代概率的期望最大化估计
摘要当在某些时间点对几个独立集落中的增殖细胞进行计数时,通过期望最大化算法获得多类型分支过程参数的最大似然估计。在后代分布由带有二叉家谱的马尔可夫分支过程控制的情况下,这种方法依赖于树的部分知识,产生与使用树的完整知识计算的估计相同的估计。
更新日期:2017-10-02
中文翻译:
一类多类型分支过程中子代概率的期望最大化估计
摘要当在某些时间点对几个独立集落中的增殖细胞进行计数时,通过期望最大化算法获得多类型分支过程参数的最大似然估计。在后代分布由带有二叉家谱的马尔可夫分支过程控制的情况下,这种方法依赖于树的部分知识,产生与使用树的完整知识计算的估计相同的估计。