The Geometric Approximation to the Cusum Run Length Distribution
CUSUM 运行长度分布的几何近似AI 解读 ↓
本页整理公开书目信息,不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成,未完成全文核验,可能有误;具体假设、证明与结论请核对原文。摘要保留来源文本,未经模型改写。
DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要;缺少可靠材料时保留待补状态。
引用量采用 OpenAlex 单条关联记录,不合计多个记录;关联记录可能包含正式发表版本,不等于此版本单独引用。缺失不视为零,引用指标不代表论文质量。
关注作者按书目中的完整姓名匹配,同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列,再参考通用方法与发表日期。
AI 根据所提供的论文材料归类:摘要仅研究 CUSUM 运行长度近似,未明确给出时间序列结构变化模型或宏观应用。
反馈分类问题CUSUM 运行长度分布的几何近似AI 解读 ↓
正在核对关联版本…
正在核对对应版本的资源…
It has long been known that at larger run lengths, the distribution of cusum run length, T, converges to the geometric form cλT. Currently, the only approximation to c is 1 and one approximation is available for λ which goes back to Page (1954). The usefulness of these approximations has never been tested. Two new approximations for c and three for λ are derived. All are compared to numerically-derived values c and λ for a small but diverse set of cusums whose increments are normally-distributed. The resulting approximations to cλT are finally compared to actual numerically-derived run length percentiles.