Original Paper
Testing Equality of Means in the Presence of Correlation and Missing Data
Abstract
A statistic, derived from the combination of two dependent tests, is proposed for testing the hypothesis of equality of the means of a bivariate normal distribution with unknown common variance and correlation coefficient when observations are missing on one or both variates. The null distribution of the statistic is approximated by a well‐known distribution. The empirical powers of the statistic are computed and compared with some of the known statistics. The comparisons support the use of the proposed test.
Citing Literature
Number of times cited according to CrossRef: 7
- Lubna Amro, Frank Konietschke, Markus Pauly, Multiplication‐combination tests for incomplete paired data, Statistics in Medicine, 10.1002/sim.8178, 38, 17, (3243-3255), (2019).
- Daniel Gaigall, Testing marginal homogeneity of a continuous bivariate distribution with possibly incomplete paired data, Metrika, 10.1007/s00184-019-00742-5, (2019).
- Lubna Amro, Markus Pauly, Permuting incomplete paired data: a novel exact and asymptotic correct randomization test, Journal of Statistical Computation and Simulation, 10.1080/00949655.2016.1249871, 87, 6, (1148-1159), (2016).
- J.S. Maritz, A PERMUTATION PAIRED TEST ALLOWING FOR MISSING VALUES, Australian Journal of Statistics, 10.1111/j.1467-842X.1995.tb00649.x, 37, 2, (153-159), (2008).
- D. S. Bhoj, Testing Equality of Correlated Means in the Presence of Unequal Variances and Missing Values, Biometrical Journal, 10.1002/bimj.4710330604, 33, 6, (661-671), (2007).
- Stuart A. Gansky, Gary G. Koch, Assessing bias of multicenter trials with incomplete treatment allocation, Journal of Statistical Planning and Inference, 10.1016/S0378-3758(00)00327-X, 96, 1, (83-107), (2001).
- Steven T. Garren, Maximum likelihood estimation of the correlation coefficient in a bivariate normal model with missing data, Statistics & Probability Letters, 10.1016/S0167-7152(98)00035-2, 38, 3, (281-288), (1998).
