Details
| Original language | English |
|---|---|
| Article number | 106837 |
| Journal | Computational Statistics and Data Analysis |
| Volume | 142 |
| Issue number | 142 |
| Early online date | 16 Sept 2019 |
| Publication status | Published - Feb 2020 |
Abstract
The Rothman–Woodroofe symmetry test statistic is revisited on the basis of independent but not necessarily identically distributed random variables. The distribution-freeness if the underlying distributions are all symmetric and continuous is obtained. The results are applied for testing symmetry in a meta-analysis random effects model. The consistency of the procedure is discussed in this situation as well. A comparison with an alternative proposal from the literature is conducted via simulations. Real data are analyzed to demonstrate how the new approach works in practice.
Keywords
- Measurement error, Meta-analysis, Not identically distributed, Random effects model, Rothman–Woodroofe statistic, Symmetry test
ASJC Scopus subject areas
- Mathematics(all)
- Statistics and Probability
- Mathematics(all)
- Computational Mathematics
- Computer Science(all)
- Computational Theory and Mathematics
- Mathematics(all)
- Applied Mathematics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Computational Statistics and Data Analysis, Vol. 142, No. 142, 106837, 02.2020.
Research output: Contribution to journal › Article › Research
}
TY - JOUR
T1 - Rothman–Woodroofe symmetry test statistic revisited
AU - Gaigall, Daniel
PY - 2020/2
Y1 - 2020/2
N2 - The Rothman–Woodroofe symmetry test statistic is revisited on the basis of independent but not necessarily identically distributed random variables. The distribution-freeness if the underlying distributions are all symmetric and continuous is obtained. The results are applied for testing symmetry in a meta-analysis random effects model. The consistency of the procedure is discussed in this situation as well. A comparison with an alternative proposal from the literature is conducted via simulations. Real data are analyzed to demonstrate how the new approach works in practice.
AB - The Rothman–Woodroofe symmetry test statistic is revisited on the basis of independent but not necessarily identically distributed random variables. The distribution-freeness if the underlying distributions are all symmetric and continuous is obtained. The results are applied for testing symmetry in a meta-analysis random effects model. The consistency of the procedure is discussed in this situation as well. A comparison with an alternative proposal from the literature is conducted via simulations. Real data are analyzed to demonstrate how the new approach works in practice.
KW - Measurement error
KW - Meta-analysis
KW - Not identically distributed
KW - Random effects model
KW - Rothman–Woodroofe statistic
KW - Symmetry test
UR - http://www.scopus.com/inward/record.url?scp=85072297509&partnerID=8YFLogxK
U2 - 10.1016/j.csda.2019.106837
DO - 10.1016/j.csda.2019.106837
M3 - Article
VL - 142
JO - Computational Statistics and Data Analysis
JF - Computational Statistics and Data Analysis
SN - 0167-9473
IS - 142
M1 - 106837
ER -