The behaviour of rank correlation coefficients for incomplete data
Open Access
- 7 August 2022
- journal article
- research article
- Published by Taylor & Francis in Research in Mathematics
- Vol. 9 (1)
Abstract
This paper presents the analysis to disclose the behaviour of rank correlation coefficients under the complete and incomplete data condition. The main concern of this research is to deal with the missing data by preserving the originality of data pair rather than experiencing data deletion or imputation. The paper introduces the variability function that is developed for each correlation coefficient in order to disclose the mean and the variance for every possible data sequences. The comparisons between Kendall, Spearman, and the absolute distance measure for index ranking demonstrate the use of variability function under both the complete and incomplete data, in which it becomes a useful tool to describe the coefficient’s mechanism to proceed with a set of possible data sequences. The analysis proves that Kendall coefficient becomes the better method compared to Spearman and the absolute distant measure due to threefold, i.e. the ability to preserve the zero mean of variability distribution in complete data, the ability to survive from the missing data, and the ability to gain a higher rate of convergence in incomplete condition. Meanwhile, Spearman fails to preserve the original data pair under the incomplete condition due to direct measurement of rank distances.Keywords
Funding Information
- research
This publication has 19 references indexed in Scilit:
- Performance measurement without ground truth to achieve optimal edgeInternational Journal of Image and Data Fusion, 2017
- Low-cost autonomous perceptron neural network inspired by quantum computationAIP Conference Proceedings, 2017
- Analyzing Incomplete Item Scores in Longitudinal Data by Including Item Score Information as Auxiliary VariablesStructural Equation Modeling: A Multidisciplinary Journal, 2015
- Examining Measure Correlations With Incomplete Data SetsStructural Equation Modeling: A Multidisciplinary Journal, 2014
- Visualizing Incomplete and Partially Ranked DataIEEE Transactions on Visualization and Computer Graphics, 2008
- Multivariate non-parametric tests of trend when the data are incompleteStatistics & Probability Letters, 2002
- Power calculations for tests of trend with missing observationsEnvironmetrics, 1999
- A simple estimator for correlation in incomplete dataStatistics & Probability Letters, 1996
- Rank correlation methods for missing dataCanadian Journal of Statistics, 1995
- The Proof and Measurement of Association between Two ThingsThe American Journal of Psychology, 1904