Using the bootstrap for statistical inference on random graphs
Using the bootstrap for statistical inference on random graphs
复制标题
DOI：
10.1002/cjs.11271
复制
发表时间：
2014-02
期刊：
影响因子：
--
通讯作者：
M. Thompson;L. Leticia Ramirez Ramirez-L.-Leticia-Ramirez-Ramirez-21103316;V. Lyubchich;Y. Gel
中科院分区：
文献类型：
--
作者：
M. Thompson;L. Leticia Ramirez Ramirez-L.-Leticia-Ramirez-Ramirez-21103316;V. Lyubchich;Y. Gel
在本文中，我们提出了一种新的非参数网络推理方法，可以看作是一个融合的块采样程序的时间和空间依赖的过程与经典的网络方法。在未知度分布的假设下，我们使用“拼凑”样本和非参数自举法来估计和量化网络平均度的不确定性。我们提供了一个启发式的理由渐近性质的建议“拼凑”抽样和目前的交叉验证方法选择一个最佳的“补丁”的大小。我们在具有短尾和长尾平均度分布的模拟网络上验证了新的“拼凑”引导，并重新访问了Erdös合作数据以说明所提出的方法。加拿大统计杂志44：3-24; 2016 © 2015加拿大统计学会
In this paper we propose a new nonparametric approach to network inference that may be viewed as a fusion of block sampling procedures for temporally and spatially dependent processes with the classical network methodology. We develop estimation and uncertainty quantification procedures for network mean degree using a “patchwork” sample and nonparametric bootstrap, under the assumption of unknown degree distribution. We provide a heuristic justification of asymptotic properties of the proposed “patchwork” sampling and present cross‐validation methodology for selecting an optimal “patch” size. We validate the new “patchwork” bootstrap on simulated networks with short‐ and long‐tailed mean degree distributions, and revisit the Erdös collaboration data to illustrate the proposed methodology. The Canadian Journal of Statistics 44: 3–24; 2016 © 2015 Statistical Society of Canada