The objective of this paper is to explore the impact of Non-oil tax revenue on the economic growth of Nigeria as proxies by the real gross domestic product (RGDP). The ordinary least square (OLS) regression analysis was adopted to explore the relationship between the RGDP (the dependent variable) and (the independent variables), company income tax, (CIT), Custom and Excise Duty, CED, Value added Tax,(VAT), Federal government independent revenue, (FGIR), and Education taxes (ET), heads over the period 1995-2015. Augmented Dickey Fuller unit root test was employed to examine the stationary properties of the series, Johansen co-integration test was applied to determine the long-run relationship among study variables while fully modified ordinary least squares co-integrating regression equation was estimated to determine the impacts of Non-oil tax revenue on RGDP. Granger causality test base on Toda and yamamoto procedure was then applied to determine the direction on causality. The ADF unit root tests indicate that all the variable is integrated of order one, 1(1). The Johansen co-integration test reveals that the variable under are co-integrated and do not wander away from each other A simple hypothesis was formulated in the null form which states that there is no significant relationship between federally collected Non-oil tax revenue and the RGDP in Nigeria. The regression result indicated a very positive and significant relationship. However some of the indicator did not have much significant RGDP as they fell below the level expected. The anomaly was attributed to dysfunctional ties in the income tax system, loopholes in tax laws and inefficient tax administration. Suggestions were made as to strategies to be adopted to improve the system of tax administration and tax policy in other to increase Non-oil tax revenue generation.

In this paper, a three parameter life time model named Type II Topp-Leone Gumbel type-2 distribution which can be used to model reliability problems, fatigue life studies, and survival data has been studied. We derived explicit expressions for some of its statistical properties such as ordinary moments, generating function, incomplete moments, and order statistics. The maximum likelihood estimation technique is used to estimate the parameters of the model. The tractability of the model was illustrated by using two real life data sets. The proposed distribution provides a better fit than some well known distributions using criteria of criteria of goodness of fit.