Nonparametric Tests of Differences in Medians: Comparison of the Wilcoxon–Mann–Whitney and Robust Rank-Order Tests
By Nick Feltovich. 2003
126 citations recorded by the source corpus.
Subfields: Economics and Econometrics, Marketing
View Paper: https://www.semanticscholar.org/paper/fc1b79a3ec9afbb649e18e40bd276af2133ab5a8
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Economics and Econometrics
- E. Chung
- John Duffy
- Joseph P. Romano
- A. Shaikh
- T. Armstrong
- P. Grieco
- Andrés Santos
- Donald W. K. Andrews
In Marketing
- E. Chung
- John Duffy
- Joseph P. Romano
- A. Shaikh
- T. Armstrong
- P. Grieco
- Andrés Santos
- Donald W. K. Andrews
Citations in the corpus
- Improving Lesion-Symptom Mapping (2007, background): “Unfortunately, both of these tests tend to generate false alarms when their assumptions are violated (Reiczigel, Zakariás, & Rózsa, 2005; Feltovich, 2003; Zumbo & Coulombe, 1997; Pratt, 1964).”
- Do short-term laboratory experiments provide valid descriptions of long-term economic interactions? A study of Cournot markets (2013, unknown): “…robust rank-order test is less sensitive to changes in sample sizes and distributional assumptions than the Wilcoxon-Mann-Whitney test (see Feltovich 2003). find any significant differences between any of the treatments when comparing the markets averaged over rounds 11 to 23 pairwise,…”
- Asymptotically valid and exact permutation tests based on two-sample U-statistics (2016, methodology): “As Feltovich (2003) pointed out, the robust rank-order test tends to outperform the Wilcoxon test under more general settings as the robust rank-order test only requires the underlying distributions to be symmetric.”
- Words, Deeds, and Lies: Strategic Behaviour in Games with Multiple Signals (2006, methodology): “See Feltovich (2003) for a simulation–based comparison of the robust rank–order and Wilcoxon–Mann–Whitney tests, under a variety of distributional assumptions.”
- Critical Values for the Robust Rank-Order Test (2005, unknown): “(See also Feltovich, 2003; Zimmerman and Zumbo, 1993a,b.) 526 Feltovich For large sample sizes, ` U is distributed approximately N(0,1), though as mentioned above, the convergence of ` U to a N(0,1) random variable is slow. distributions and record the resulting values of ` U ; the…”