1977
DOI: 10.1080/03610927708827533
|View full text |Cite
|
Sign up to set email alerts
|

Robust regression using iteratively reweighted least-squares

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

4
1,035
0
8

Year Published

1998
1998
2017
2017

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 1,762 publications
(1,047 citation statements)
references
References 10 publications
4
1,035
0
8
Order By: Relevance
“…Since most traditional or generalized linear regression approaches are very sensitive to outliers 23 and since many of the examined cancer samples are hypermutators (i.e., outliers), we leveraged a robust regression model. The robust regression iteratively reweights least squares with a bi-square weighting function and overcomes some (if not most) of the limitations of traditional approaches [24][25][26] . Similarly, we report results using Spearman's rank correlation coefficient since it is more robust to data outliers when compared to Pearson's product-moment correlation coefficient 27 .…”
Section: Statistical Analysis Of Relationships Between Age and Mutationsmentioning
confidence: 99%
“…Since most traditional or generalized linear regression approaches are very sensitive to outliers 23 and since many of the examined cancer samples are hypermutators (i.e., outliers), we leveraged a robust regression model. The robust regression iteratively reweights least squares with a bi-square weighting function and overcomes some (if not most) of the limitations of traditional approaches [24][25][26] . Similarly, we report results using Spearman's rank correlation coefficient since it is more robust to data outliers when compared to Pearson's product-moment correlation coefficient 27 .…”
Section: Statistical Analysis Of Relationships Between Age and Mutationsmentioning
confidence: 99%
“…The model described in (7) was fitted separately for the observations contained in each class using a robust linear least squares algorithm (bi-square-weighted iterations) (Holland andWelsch 1997, DuMouchel andO"Brien 1989). Using k i ", k g " and k v ", all PRI observations within each class were normalized to a constant view and illumination geometry (June 21 st solar noon, looking north at a vertical zenith angle of 62 ) to separate physiologically induced changes in PRI from those caused by other effects and permit the examination of changes in canopy NDRI strictly as a function of towermeasured .…”
mentioning
confidence: 99%
“…Помимо суммирования по всем типам спиральных пар, мы расширим сравнение, включив в него вероятность log(r/d), вычисленную для объединения множеств {A} и {B}. Асимптотическая часть логарифма вероятности как функция логарифма соотношения расстояний аппроксимировалась линейной зависимостью по методу [27]. Данные для регрессии выбирались в диапазоне 0.5 < log(r/d) < 5.…”
Section: регрессионный анализ гистограмм распределения спиральных парunclassified