Adetunji,A.A et. al. /International Journal of Modern Sciences and Engineering Technology (IJMSET) ISSN 2349-3755; Available at https://www.ijmset.com Volume 1, Issue 4, 2014, pp.55-59 © IJMSET-Advanced Scientific Research Forum (ASRF), All Rights Reserved “ASRF promotes research nature, Research nature enriches the world’s future” 55 Test for Ordered Alternative in Location Tests, an Application to Students Admission Abstract Education is an instrument par excellence for effecting national development but the rate of admission denial in higher institution of learning in Nigeria is getting beyond reach. Infrastructure expansion is on the downward trend with associated higher demand for admission into various institution. This research paper observes the rate of admission in Nigeria with particular reference to the Federal Polytechnic, Ado-Ekiti, Ekiti State, Nigeria over a period of ten years. Jonckheere-Terpstra Nonparametric ordered alternative test was used and the result shows a significant increase in the number of admitted students over the sampled period. The results indicate an important need for the government to see to the establishment of more institutions of higher learning and ensure proper funding of the various established higher institutions to enable them their infrastructures. Keywords: Nonparametric, Admission, Students, and Jonckheere-Terpstra 1. INTRODUCTION: In statistical modelling, a parametric statistic distribution of model involves several unknown constants called parameters. However, non-parametric statistics (also called “distribution free statistics”) means the statistics do not assume data or population have any parameters (such as mean and variance) or characteristic structure (such as normal distribution) [1] . The methods are often the only method available for data that simply specify order or counts of numbers of events or of individuals in various categories since those populations do not have normal distribution. Also, the method can be of great advantage because of its easy usage and when the parametric equivalent is not available or the available one is highly cumbersome to utilise. Most of the parametric techniques have their non-parametric equivalent. In the parametric test, there is one-sample t-test (Wilcoxon Signed-Rank test), two-sample t-test (Wilcoxon Rank-Sum test), and one way ANOVA (Kruskal-Wallis test). The Kruskal-Wallis test is an omnibus test and is used to compare population location parameters among two or more groups based on independent samples. If the expectation is on the nature of the data is that there is trend in the data (mostly increasing), the researcher may want to test hypotheses about mean or median (θ i ) for H 0 : all θ i are equal against H A : θ 1 ≤ θ 2 ≤ θ 3 ≤ … ≤ θ k with at least one of the inequalities is strict. In this case, a special case of Kruskal-Wallis test which is called Jonckheere-Terpstra is used. Nonparametric Statistics Nonparametric statistics included descriptive and inferential statistics not based on paramatrized families of probability distributions. The ty mm pical parameters are the mean, variance, etc. Unlike parametric statistics, nonparametric statistics make no assumptions about the probability distributions of the variables being assessed [2] . Definitions In statistics, the term "non-parametric statistics" has at least two different meanings: 1. The first meaning of non-parametric covers techniques that do not rely on data belonging to any particular distribution. These include, among others: · distribution free methods, which do not rely on assumptions that the data are drawn from a given probability distribution. As such it is the opposite of parametric statistics. It includes non- parametric descriptive statistics, statistical models, inference and statistical tests. Adetunji, A. A. 1 Department of Mathematics and Statistics, Federal Polytechnic, Ado- Ekiti, Ekiti State, Nigeria adecap4u@yahoo.com Ige, S. O. 2 Department of Mathematics and Statistics, Federal Polytechnic, Ado-Ekiti, Ekiti State, Nigeria samolu123@yahoo.com