The null distribution of sample serial correlation coefficient |
| |
Authors: | S. Yue C. Y. Wang |
| |
Affiliation: | (1) MSC-Ontario Region, Environment of Canada, CCIW, 867 Lakeshore Rd., P.O. Box 5050, Burlington, Ontario, Canada L7R 4A6 E-mail: sheng.yue@ec.gc.ca, CA;(2) Development Research Center of Water Resources Ministry of China, DeWai LiuPuKang, Beijing 100011, China, CN |
| |
Abstract: | The null distribution of the lag-k sample serial correlation coefficient (r k , k=1,2,3) was investigated by Monte Carlo simulation. For a time series with normal, exponential, Pearson 3, EV1 (Gumbel), or generalized Pareto (GP) distribution type, the null distribution of its r k can be approximated by the normal distribution with mean −1/(n−k) and variance 1/(n−1). But for a time series with the lognormal, EV2 or EV3 (Weibull) distribution type, the null distribution of r k is skewed distributed. In such cases, a simulation technique is suggested to construct percentile confidence intervals at a given significance level. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|