1985
DOI: 10.1086/163225
|View full text |Cite
|
Sign up to set email alerts
|

Statistical methods for astronomical data with upper limits. I - Univariate distributions

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

13
701
0

Year Published

2002
2002
2017
2017

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 677 publications
(714 citation statements)
references
References 0 publications
13
701
0
Order By: Relevance
“…The value of W does not change significantly between halo masses of -10 11 13  M for the entire sample. 18 The test was performed on our censored data using the astronomy survival analysis code ASURV (Feigelson & Nelson 1985). ASURV is capable of handling single-and double-censored data.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…The value of W does not change significantly between halo masses of -10 11 13  M for the entire sample. 18 The test was performed on our censored data using the astronomy survival analysis code ASURV (Feigelson & Nelson 1985). ASURV is capable of handling single-and double-censored data.…”
Section: Discussionmentioning
confidence: 99%
“…The distribution can be fit as a exponential with a scale-length of 1.1R vir , i.e., Å = , where the normalization factor, A, is equal to 0.9 Å. The fit was derived using the Buckley-James 17 method (Buckley & James 1979) and Expectation-maximization algorithm as implemented in the survival analysis software package, ASURV (Feigelson & Nelson 1985). The equivalent width data presented here are the same as that of Figure2 of Borthakur et al (2015), however, the abscissa is different, because we have adopted the Kravtsov et al (2014), Liang & Chen (2014) formalism with modifications based on the findings of Mandelbaum et al (2016) for halo masses and virial radii.…”
Section: Structurementioning
confidence: 99%
“…In order to account for the upper limits in our sample, we also use statistical methods that are often generalizations of these classical non-parametric test. We use the astronomical survival analysis package (ASURV; Feigelson & Nelson 1985). Using three different tests, the Gehans Generalized Wilcoxon test; the log-rank test; and the Peto and Peto Generalized Wilcoxon test, the difference in the RLs and RLQs distributions of the FIR luminosity is confirmed at > 98.9, > 99.3, and > 98.9 per cent confidence level, respectively.…”
Section: Fir-radio Correlationmentioning
confidence: 99%
“…We have tested the statistical significance of the correlation using the computer package ASURV Rev 1.2, developed by Isobe, La Valley & Feigelson (La Valley et al 1992), which implements the methods presented in Feigelson & Nelson (1985) and in Isobe et al (1986). For sources with S (1.4 GHz) ≥ 80 mJy the test by Cox proportional hazard model yields a global χ 2 , with one degree of freedom, of 573 for flat-spectrum and of 800 for steep-spectrum sources.…”
Section: Polarization Properties Of Extragalactic Radio Sourcesmentioning
confidence: 99%