A Note on Confidence Bands for a Regression Line over a Finite Range
有限区间内回归直线置信带的一则说明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:摘要研究一般简单线性回归的置信带,没有所列领域细分的直接文本依据。
有限区间内回归直线置信带的一则说明AI 解读 ↓
正在核对关联版本…
正在核对对应版本的资源…
In a recent article Graybill and Bowden give a method for constructing a confidence band for the entire regression line in simple linear regression. Each bound consists of two straight line segments rather than of the usual branch of a hyperbola. The method uses tables of the studentized maximum modulus with parameter m = 2 and d.f. = n − 2.The present note suggests a method for obtaining linear confidence bands designed to be used over a finite range rather than from − ∞ to + ∞. The method makes use of the distribution of the studentized maximum modulus for m = 3. It is shown that if the range is of reasonable size, the band is shorter than that suggested by Graybill and Bowden except close to the midpoint of the range.In general, over most of the range of the independent variate in which one would be interested, neither line-segment method gives bands narrower than the bands of the usual hyperbola.