连续型信息资源分布的理论模型及计量分析

Theoretical Model and Bibliometric Analysis for a Continuous Information Resources Distribution

本文指出了普赖斯的连续型信息资源分布模型实质上是在文献总数与作者总数成正比这一假设下建立起来的。其不足之处是没有考虑到现代信息传递手段和信息获取的现代工具等诸多因素。为了弥补这一不足，我们在普赖斯的模型的基础上纳入这些因素，得到了本文中的理论模型（8）。对改进的模型，我们进行了分析，得到了三个基本结论。针对主题“数据挖掘”在相关杂志上采得样本，并做了数据整理。利用整理后的数据，使用EViews软件，对所得的模型进行计量分析，得到经验模型（11）。经验模型的行为和理论模型的行为是一致。

The essence that Price＇ s model is based on the hypothesis that total sum of papers is in the positive ratio of total sum of workers of these papers is analysis in the paper. This paper sets forth continuous information resources distribution theoretical model （8） based on Price＇s continuous information resources distribution model under taking into account advance tools and means of information transmission and collection. Analyzing the new model, three basic results have been gained in the paper. For the subject ＂data mining＂, we take samples from some relative journal, and death with these sample data. By way of EViews tool and new data, the model modeled has been estimated. And we have obtained that the experience model （ 11 ） of this new model, with which behavior of the new theoretical model is consistent in the paper.