1992
DOI: 10.1007/978-94-011-2546-8_20
|View full text |Cite
|
Sign up to set email alerts
|

A Rank-Invariant Method of Linear and Polynomial Regression Analysis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

4
1,372
0
11

Year Published

1996
1996
2017
2017

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 1,533 publications
(1,387 citation statements)
references
References 3 publications
4
1,372
0
11
Order By: Relevance
“…For this purpose, another nonparametric method referred to as the Theil-Sen (TS) approach is very popular among researchers to quantify the slope of the trend (magnitude). TS was originally described by Theil [69] and Sen [70]. This approach provides a more robust slope estimate than the least squares method because it is insensitive to outliers or extreme values and competes well against simple least squares even for normally distributed data in a time series [71,72].…”
Section: Resultsmentioning
confidence: 99%
“…For this purpose, another nonparametric method referred to as the Theil-Sen (TS) approach is very popular among researchers to quantify the slope of the trend (magnitude). TS was originally described by Theil [69] and Sen [70]. This approach provides a more robust slope estimate than the least squares method because it is insensitive to outliers or extreme values and competes well against simple least squares even for normally distributed data in a time series [71,72].…”
Section: Resultsmentioning
confidence: 99%
“…The regression models are specific to each site, and are not intended as predictive tools, but rather as a means to provide insight into the nature of the relationship between the response and explanatory variables. Kendall's tau correlation coefficients (s) [Kendall, 1975] and Kendall-Theil lines [Theil, 1950] were generated to describe the relationships between k and daily variability in dissolved oxygen concentration. All statistical analyses were conducted using R (http://r-project.…”
Section: Methodsmentioning
confidence: 99%
“…The values are obtained from linearization of the curve segments with respect to intervals of ± 0.15 N around the force values of ± 0.8 N and of + 0.55 Nmm around moment values of ± 4 Nmm (Fig. 6) by using distribution-free estimation methods (Dawson-Saunders and Trapp, 1990;Theil, 1950). The load ranges were chosen such as to cover enough data points around the selected load levels and to cover a more-or-less linear region in the upper and lower branch in the curve.…”
Section: Methodsmentioning
confidence: 99%