The outlier values in the performance of students on the tests of abilities and achievement and the impact of the method of dealing with them in the results of statistical analyzes

Document Type : Original Article

Author

Abstract

The study aimed to determine the outlier values ​​in the students' grades in the ability and achievement tests and the effect of the method of dealing with them in the results of the statistical analyzes. To achieve the objectives of the study, a stratified random sample of (200) students was selected for each of the two tests. With the outlier values ​​on the results of t-test for the independent samples, one-way ANOVA and the simple linear regression analysis. The t-test of two independent samples showed different results where the practical significance and the strength of the test were in the cases of deletion or replacement of the outlier values. The results of the regression are different according to the method of dealing with the outlier values, The results showed that the achievement test was a good predictor of ability testing

Keywords


Adeboye, A. James, N. & Akinwumi, O. (2016). Assessment of Outlier Detection Procedures in Analysis of Regression Model. Department of Biostatistics and Epidemiology, Pakistan Journal of Social Sciences, University of Fort Hare, 13(3), 25-31.
Al-Fatal, H. & Interanick, E. (2009). Explore and estimate extreme values in some nonlinear models. Journal of Management and Economics, Mustansiriya University, 77, 214-224.
Al-Nour, N. (2010). Comparison of some robust methods to estimate the location parameter of some probability distributions. Kufa Journal of Mathematics and Computers, University of Mustansiriya, 1(1), 1-22.
Ampanthong, P. & Suwattee, P. (2009). A comparative Study of Outlier Detection Proceedings in Multiple Linear Regression. Proceedings of the International Multiconference of Engineers and Computer Scientists, Vol.1, IMECS, Hong Kong.
Barnett, V. & Lewis, T. (1977). Outlier in Statistical Data. and Sons, Third Edition. New York: John Wiley.
Dan, E. D. & Ijeoma, O. A. (2013a). Statistical Analysis/Methods of Detecting Outliers in A Multivariate Data in A Regression Analysis Model. Journal of International Academic Research for Multidisciplinary, 1(3), 302-337.
Green, R.F. (1976). Outlier-prone and Outlier-Resistant Distribution, Jornal of The American Statistical Association, 71, p. 502-505.
Hadi, F. (2010). Study of the effect of extreme values on the Box-Jenkins and Furer methods. Qadisiyah Journal of Administrative and Economic Sciences, Al-Qadisiyah University, 12(3), 121- 134.
Hair, J.F., Black, W.C., Babin B.J., Anderson, R.E., Tatham, R.L.(2006). Multivariate Data Analysis. Pearson International Education,(6^end edittion). New Jersey.
Hawkins, D.M. (1980). Identification of outlier. London: Chapman and Hall.
Kassem, M. & Ismail, Y. (2008). Expose extreme values in Bez style using a Gypsum preview. Iraqi Journal of Statistical Sciences, University of Mosul, 14, 88-68.
McClave, J.T. & Sincich, T. (2000). Statistics.(Eighth Edition). Prentice Hall, New Jersy. pp.147-155.
Rahman, M. & Al Amri, K. (2011). Effect of Outlier on Coefficient of Determination. International Journal of Education Research, Academic Journal, 1(6). P 9.
Rahman, M. & Al Amri, K. (2011). Effect of Outlier on Coefficient of Determination. International Journal of Education Research, Academic Journal, 1(6). P 9.
Tukey, J.W. (1962). The Future of Data Analysis. Ann, Math, Statist.
Tukey, J.W. (1977). Exploratory Data Analysis. Addison-Wesley Redding, MA, USA.
Walfish, S.(2006). A Review of Statistical Outlier Methods, Pharmaceutical Technology, pp. 1-5
Yousef, A. (2015). The effect of Outliers in multiple linear regression regression model parameters. A magister message that is not published. Sudan University of Science and Technology, Khartoum.