Parameters behind “Nonparametric” Statistics: Kendall's tau, Somers’ D and Median Differences

By R. Newson. 2002

407 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/61a99e39045e4cfba75528be55040300ab7b0075

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Response Order Effects in Dichotomous Categorical Questions Presented Orally The Impact of Question and Respondent Attributes (2007, background): “For dichotomous response order experiments, this is equal to the difference between the percent of respondents who chose a response option when it was presented last and the percent of respondents who chose that response option when it was presented first (Newson 2002).”
Effect Size in Single-Case Research: A Review of Nine Nonoverlap Techniques (2011, methodology): “Tau is obtained from either Kendall’s rank correlation (KRC) or from the Mann-Whitney U test, but both require minor hand calculations (Newson, 2001).”
The Wilcoxon–Mann–Whitney Procedure Fails as a Test of Medians (2018, background): “Newson (2002) notes that a “dominance diagram” will also give a graphical representation of P̂r(X Y ) + P̂r(X = Y )/2.”
Performance evaluation of the English Premier Football League with data envelopment analysis (2006, methodology): “In Table 4 we present the Mann–Whitney U-test, between efficiency scores obtained using the CCR model for all clubs in all years and points obtained at the end of the season (Newson, 2002).”
Comparing the Predictive Powers of Survival Models Using Harrell's C or Somers’ D (2010, methodology): “An overview of the parameter family is given in Newson (2002), and the methods and formulas are given in detail in Newson (2006a,b,c).”
What Hypotheses do “Nonparametric” Two-Group Tests Actually Test? (2012, background): “This measure, usually called the Hodges– Lehman median difference (Hodges and Lehmann 1963) is, as Newson (2002) points out, a special case of Theil’s (1950a; 1950b; 1950c) median slope.”
Can models of presence‐absence be used to scale abundance? Two case studies considering extremes in life history (2005, methodology): “Probability of occurrence for each observation was estimated and compared to observed abundance using a Somers’ D statistic (ranging from /1 for complete discordance to 1 for complete concordance; Somers 1962, Newson 2001).”
Confidence Intervals for Rank Statistics: Somers’ D and Extensions (2006, background): “…k=1 φ (XY ) kk − 2 ( φ (XY ) j+ − φ(XY )jj )} (13) If the user specifies funtype(vonmises), then the point estimates of the population von Mises functionals are the corresponding sample von Mises functionals, or V statistics in the terminology of Riedwyl (1988) and of chapter 5 of Serfling (1980).”
An improved effect size for single-case research: nonoverlap of all pairs. (2009, methodology): “In addition, CIs are calculated by specially developed software by Newson (2000, 2002) as add-on macros for Stata statistical software .”