论文部分内容阅读
自1960年伯顿和凯布勒给出了“老化解析式”的引文分布函数以来,该公式已被情报学界认为是经典。十多年来,该公式已引起了我国情报学界的关注,并已有多人发表文章阐述各自对该公式的理解。笔者认为,多数人对该公式的理解是符合原文的意思,但也有少数的解释是与原意不符的。或几乎是“颠倒”的。我们认为,出现这些混乱的解释,是因为对统计学上常用的根据统计数据进行函数拟合,并得出分布函数或密度函数这一过程不太了解。因此有必要从概率统计的角度对该公式进行讨论,并根据我们的引文时间分布统计和曲线拟合的实践,对该公式略作评价。
This formula has been considered by the intelligence community to be a classic since Citation and Burton gave the citation distribution function of “aging analysis” in 1960. For more than a decade, the formula has drawn the attention of the intelligence community in our country and many people have published articles explaining their respective understandings of the formula. The author believes that most people understand the formula is in line with the original meaning, but there are a few explanations are inconsistent with the original meaning. Or almost “upside down”. We believe that these confusing explanations arise because we do not know much about the commonly used statistical fitting of statistics and the derivation of distribution functions or density functions. Therefore, it is necessary to discuss this formula from the perspective of probability and statistics, and to evaluate the formula based on our citation time distribution statistics and curve fitting practice.