评论:评估计数观测时间序列模式预测的准确性

Comment: Assessing the Accuracy of Time Series Mode! Forecasts of Count Observations

Journal of Business & Economic Statistics · 1989
被引 3
人大 AABS 4

中文导读

提出两种评估Harvey-Fernandes模型预测准确性的方法:一是采用气象预报员准确度评估指标,二是用非参数预测模型作为基准,并以英格兰对苏格兰进球数据为例说明。

Abstract

In this article, I suggest two approaches for assessing the accuracy of the Harvey-Fernandes model forecasts. First, I suggest using measures of forecast accuracy that were originally developed to assess and compare the accuracy of weather forecasters. Second, I suggest using a simple nonparametric forecasting model, originally developed for use with computerized inventory-control algorithms, as a benchmark against which to gauge the amount of improvement afforded by the more sophisticated Harvey-Fernandes models. I illustrate these two approaches using Harvey and Fernandes's first data example-goals scored by England against Scotland.

计数时间序列预测预测精度评估非参数基准模型