PREDICTING FERTILITY STATUS BY ADJUSTING FOR TIES IN A MATCHED SAMPLED POPULATION IN EBONYI STATE USING MEDIAN TEST

Abstract

Background and Aim of the study: The use of nonparametric methods in statistical procedures occurs when samples drawn fails to satisfy the necessary assumptions of continuity and normality required for their use by their parametric counterpart. We proposed and developed ties adjusted median test for determining desired fertility goals in a paired sampled population. This is an improved alternative to the ordinary Sign test and the Wilcoxon Signed Rank test. Methodology: The proposed method adapted the method of extended median test for matched samples but in this case adjusted for possible tied observations in the data where observations or scores may be measurements on as low as the ordinal scale. Chi-square test statistic of null hypothesis of equality of population or treatment medians was used. Results: The data for illustrating the proposed method was drawn from the actual and desired family sizes of a random sample of women from a certain community. Applying the data in testing the null hypothesis that women from the community sampled do not differ in the actual and desired number of children  showed that Using the same data, sign test gave P-value=0.0193 while Wilcoxon Signed Rank test gave P-value=0.0139 Conclusions: Results showed that the proposed method is more powerful than the ordinary Sign test and the Wilcoxon Signed Rank test at 5% significant level and hence is likely to have a higher probability of correctly rejecting a false null hypothesis.

Keywords:

extended median test, sign test, paired samples, Wilcoxon Signed Rank Sum test, chi-square test

References

Gibbons, J. D. (1993). Nonparametric Statistical; An Introduction, Newbury Park, Sage Publication. Pp. 180-220.

Oyeka, C. A. (2013). An Introduction to Applied Statistical Methods. Ninth Edition, Nobern Avocation Publishing Company, Enugu.

Oyeka, I. C. A., Ebuh, G. U., Nwosu, C. R., Utazi, E. C., Ikpegbu, P. A., Obiora-Ilouno, H., & Nwankwo, C. C. (2009). A Method of Analysing Paired Data Intrinsically Adjusted for Ties. Global Journal of Mathematics and Statistics, India. 1(1), 1-6.

Ebuh, G. U. & Oyeka, I. C. A. (2012). Statistical Comparison of Eight Alternative Methods for the Analysis of Paired Sample Data with Applications. Open Journal of Statistics (OJS), 2(3), 328-345.

Corder, G. W. and Foreman, D. I. (2014). Nonparametric Statistics: A step-by-step Approach, Wiley. ISBN 978-1118840313.

Siegel, S. and Castellan, N. J. Jr. (1988). Nonparametric Statistics for the Behavioral Sciences. New York, McGraw-Hill.

Gibbons, J. D. and Chakraborti, S. (2003). Nonparametric Statistical Inference. Fourth Edition, Revised and Expanded, Marcel Dekker, New York.

Friedlin, B. and Gastwirth, J. L. (2000). Should the median test be retired from general use? The American Statistician, 54, 161-164.

Gart, J. J. (1963). A Median Test with Sequential Application. Biometrika, vol. 50, pp. 55-62.

Afuecheta, E. O., Oyeka, I. C. A, Ebuh, G. U., & Nnanatu, C. C. (2012). Modified Median Test Intrinsically Adjusted for Ties. Journal of Basic Physical Research, 3, 30-34.

Oyeka I. C. A. and Uzuke C. A. (2011). Modified extended median test. African Journal of Mathematics and Computer Science Research Vol. 4(1), pp. 27-31.