mailto:uumlib@uum.edu.my 24x7 Service; AnyTime; AnyWhere

Using real life data to validate the winsorized modified Alexander-Govern test

Ochuko, Tobi Kingsley and Abdullah, Suhaida and Zain, Zakiyah and Syed Yahaya, Sharipah Soaad (2016) Using real life data to validate the winsorized modified Alexander-Govern test. International Journal of Statistics and Applications, 6 (2). pp. 45-52. ISSN 2168-5193

[thumbnail of IJSA 6 2 2016 45-52.pdf] PDF
Restricted to Registered users only

Download (435kB) | Request a copy

Abstract

To evaluate the efficiency and reliability of the Alexander-Govern (AG) test and the Winsorized Modified One Step M-estimator in the Alexander-Govern (AGWMOM) test, using real life data. Methods: Test of homogeneity of variance was done from real life data, comprising of young, middle and old groups, using the Levene’s test to see if the three groups are different from each other or not as the reaction time changes.Descriptive statistics, Test of normality and Test Statistic were performed for the three independent groups, to evaluate the reliability and efficiency of the tests. Results: The p-value from the test of homogeneity of the variance is greater than 0.05, i.e 0.174 > 0.05 and it shows that we accept HO and conclude that there is no difference between the groups as the reaction time changes.The descriptive statistics show that the AGWMOM test has a smaller standard error compared to the AG test.The result of the test statistic reveals that the AGWMOM test produced a p-value of 0.0000002869 that is considered to be significant compared to the AG test that produced a p-value of 0.0698 that is regarded as not significant, since its p-value is > 0.05. Conclusions: The AGWMOM test is more efficient and reliable in minimizing error as much as possible from the real life data, because the test produced a smaller standard error from the real life data in comparison to the AG test and is regarded as significant.

Item Type: Article
Uncontrolled Keywords: Alexander-Govern (AG) test, AGWMOM test and Test Statistic
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: School of Quantitative Sciences
Depositing User: Dr. Suhaida Abdullah
Date Deposited: 08 Aug 2016 03:38
Last Modified: 04 Dec 2016 08:01
URI: https://repo.uum.edu.my/id/eprint/18469

Actions (login required)

View Item View Item