arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1404.3219stat.MLnlin.CDq-fin.ST
收藏

不做回归估计非线性回归误差

Estimating nonlinear regression errors without doing regression

Hong Pi, Carsten Peterson

摘要:

提出了一种不进行回归而估计非线性回归误差及其分布的方法。假设建模函数的连续性,方差以从数据中提取的条件概率给出。对于N个数据点,计算需求为N2。将预测的残余误差与从线性模型假设导出的残余误差进行比较提供了非线性的信号。该方法成功地说明了由Ikeda和Lorenz地图与噪声增强所产生的数据。作为一个副产品,这些地图的嵌入尺寸也被提取。

英文摘要:

A method for estimating nonlinear regression errors and their distributions without performing regression is presented. Assuming continuity of the modeling function the variance is given in terms of conditional probabilities extracted from the data. For N data points the computational demand is N2. Comparing the predicted residual errors with those derived from a linear model assumption provides a signal for nonlinearity. The method is successfully illustrated with data generated by the Ikeda and Lorenz maps augmented with noise. As a by-product the embedding dimensions of these maps are also extracted.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑