Doornik Jurgen A, Hendry David F, Shephard Neil
Nuffield College, University of Oxford, Oxford OX1 1NF, UK.
Philos Trans A Math Phys Eng Sci. 2002 Jun 15;360(1795):1245-66. doi: 10.1098/rsta.2002.0994.
This paper reviews the need for powerful computing facilities in econometrics, focusing on concrete problems which arise in financial economics and in macroeconomics. We argue that the profession is being held back by the lack of easy-to-use generic software which is able to exploit the availability of cheap clusters of distributed computers. Our response is to extend, in a number of directions, the well-known matrix-programming interpreted language Ox developed by the first author. We note three possible levels of extensions: (i) Ox with parallelization explicit in the Ox code; (ii) Ox with a parallelized run-time library; and (iii) Ox with a parallelized interpreter. This paper studies and implements the first case, emphasizing the need for deterministic computing in science. We give examples in the context of financial economics and time-series modelling.
本文回顾了计量经济学中对强大计算设施的需求，重点关注金融经济学和宏观经济学中出现的具体问题。我们认为，该领域因缺乏易于使用的通用软件而受到阻碍，这种软件能够利用廉价的分布式计算机集群。我们的应对措施是在多个方向上扩展第一作者开发的著名矩阵编程解释语言Ox。我们指出了三种可能的扩展级别：（i）Ox代码中显式并行化的Ox；（ii）具有并行运行时库的Ox；（iii）具有并行解释器的Ox。本文研究并实现了第一种情况，强调了科学中确定性计算的必要性。我们在金融经济学和时间序列建模的背景下给出了示例。
