Predictive Modeling with Longitudinal Data
Predictive Modeling with Longitudinal Data
复制标题
使用纵向数据进行预测建模
DOI：
10.1080/10920277.2007.10597466
复制
发表时间：
2007
影响因子：
1.4
通讯作者：
J. Robinson
中科院分区：
文献类型：
--
作者：
M. Rosenberg;E. Frees;Jiafeng Sun;Paul H. Johnson;J. Robinson
近年来，复杂的计算机软件的发展和可用性为精算师和其他金融分析师使用预测建模提供了便利。预测建模已经在健康、财产和意外事故部门的几个应用中使用。这些应用程序通常采用特定行业技术的扩展，并没有充分利用数据中包含的信息。相比之下，我们采用基本的统计方法进行预测建模，可以在各种学科中使用。正如本文所演示的那样，该方法允许有纪律的方法来构建模型，包括模型开发和验证阶段。本文旨在为有兴趣通过使流程更加透明来使用预测建模的分析人员提供教程。本文说明了使用威斯康星州养老院成本报告的预测建模过程。我们调查了1989年至2001年间约400家疗养院的使用情况。由于数据在横截面和随时间变化，我们采用纵向模型。本文演示了分析人员在分析纵向医疗保健数据时面临的许多常见困难，以及解决这些困难的技术。我们发现使用历史趋势信息的纵向方法明显优于不利用历史趋势的回归模型。
Abstract The recent development and availability of sophisticated computer software has facilitated the use of predictive modeling by actuaries and other financial analysts. Predictive modeling has been used for several applications in both the health and property and casualty sectors. Often these applications employ extensions of industry-specific techniques and do not make full use of information contained in the data. In contrast, we employ fundamental statistical methods for predictive modeling that can be used in a variety of disciplines. As demonstrated in this article, this methodology permits a disciplined approach to model building, including model development and validation phases. This article is intended as a tutorial for the analyst interested in using predictive modeling by making the process more transparent. This article illustrates the predictive modeling process using State of Wisconsin nursing home cost reports. We examine utilization of approximately 400 nursing homes from 1989 to 2001. Because the data vary both in the cross section and over time, we employ longitudinal models. This article demonstrates many of the common difficulties that analysts face in analyzing longitudinal health care data, as well as techniques for addressing these difficulties. We find that longitudinal methods, which use historical trend information, significantly outperform regression models that do not take advantage of historical trends.
影响因子：
3.5
作者：
Deb, P;Trivedi, PK
通讯作者：
Trivedi, PK