摘要:

This paper analyzes the power of twoLmoment and the probability plot correlation coefficient (PPCC) goodness‐of‐fit tests for the Gumbel distribution and the impact of autocorrelation. The twoLmoment tests are the kappa test suggested by Hosking et al. (1985) using biased PWM estimators, and theL‐Cstest suggested by Chowdhury et al. (1991) using unbiased PWM estimators. The generalized extreme value (GEV) distribution with various values of the shape parameterκwas used as the parent distribution. Results show that theLmoment‐based tests outperform the PPCC test for independent data, or data with small autocorrelations (ρ ≤ 0.4). For high autocorrelation (ρ = 0.8), all tests are invalid because the type 1 error probability is larger than the target value. An example demonstrates consistency problems with scale and shape parameters estimated using the biased PWM estimators; these cause us to advise against their use and to recommend instead unbiased PWM estimators that employ a sample's order statistics. Overall, this paper provides another endorsement of the use of unbiasedLmoment estimators for goodness‐of‐fit tests and distribution selection, as well as a recommendation for para

ISSN:0043-1397    

DOI:10.1029/94WR02538

年代:1995

数据来源: WILEY

摘要:

In a recent paper, Philip analyzed horizontal redistribution with capillary hysteresis. He considered the special case for which one semi‐infinite half of a column has an initial condition corresponding to the point where the boundary wetting curve joins the boundary drying curve and the other semi‐infinite half of the column has an initial condition corresponding to the point where the boundary drying curve joins the boundary wetting curve. The similarity solution of this problem developed by Philip can be generalized to cases involving any uniform initial conditions of the semi‐infinite halves of the column, corresponding to arbitrary histories of the pressure head and the water content. For any such pair of initial conditions for the semi‐infinite halves, one of the following three possibilities will apply: (1) no flow between the two halves; (2) conventional flow from the wet half to the dry half; or (3) nonconventional flow from the dry half to the w

ISSN:0043-1397    

DOI:10.1029/94WR02382

年代:1995

数据来源: WILEY

ISSN:0043-1397    

DOI:10.1029/94WR01672

年代:1995

数据来源: WILEY

ISSN:0043-1397    

DOI:10.1029/94WR01671

年代:1995

数据来源: WILEY

ISSN:0043-1397    

DOI:10.1029/94WR02377

年代:1995

数据来源: WILEY

ISSN:0043-1397    

DOI:10.1029/94WR02378

年代:1995

数据来源: WILEY

ISSN:0043-1397    

DOI:10.1029/94WR02381

年代:1995

数据来源: WILEY

ISSN:0043-1397    

DOI:10.1029/94WR02510

年代:1995

数据来源: WILEY