Journal of Biometrics & Biostatistics

Intrinsically Ties Adjusted Sign Test by Ranks

Abstract

Oyeka ICA

 This paper proposes and discusses a non-parametric statistical method for the analysis of paired or matched sample data based on ranks rather than on the raw scores themselves. The proposed method intrinsically and structurally adjusts the test statistic for the possible presence of tied observations between the sampled populations and hence obviates the need to require these populations to be continuous. The number k used in the ranking may be any real number and does not affect the result of the analysis. The proposed method can be used with both numeric and nonnumeric measurements on as low as the ordinal scale and is easily modified for use with one sample data. The method is illustrated with some data and shown to compare favorably with the usual sign test and the Wilcoxon signed rank sum test in cases where these two methods may be equally used in data analysis.