Federal University Of Wukari, Nigeria

 Journal

 Comparative Analysis Of Some Sampling Techniques For The Estimation Of Registered Life Birth

 Akinola Oladiran Adepetun

 2023

In this paper, comparative analysis of three different sampling techniques which are simple random sampling, stratified random sampling and systematic random sampling for the estimation of registered life birth were investigated. The real data set for the study was obtained from Seychelles National Bureau of Statistics on the registered life birth between 1986 and 2018. The mean and variance of each sampling technique were computed and their efficiency compared using the variance criterion. The study revealed that simple random sampling is the best as it has the least variance compared with two other sampling techniques under study. 

 Faculty Of Education, Nnamdi Azikiwe University, Nigeria

 Journal

 Statistical Analysis Of The Effect Of Gender And Other Variables On Academic Performance Of Some Undergraduate University Students In Nigeria

 Akinola Oladiran Adepetun

 2023

Enhancing the capabilities and potential of a person is done through education. It is a process designed to provide him with knowledge, skills, and attitudes that will help him handle life. The academic performance based on the evaluation criteria of his institution might be used to measure how much the method has affected these people. This study, therefore, is carried out to examine how gender and other variable factors affect students' academic performance in the University. In order to acquire the data required for the study, concise survey questionnaires were administered at random to some students in the Department of Statistics of the University. The independent sample t-test was used to compare academic performance differences between gender classes, while the regression procedure was used to assess the dependency of academic performance on gender. The results of the study as presented in tables clearly show that student’s performance differs by gender classes and that the difference is statistically significant. Additionally, it was discovered that gender significantly affected students' academic performance which emphasizes the significance of gender discrepancies in students' academic performance 

 Gnedenko Forum

 Journal

 Moving Block Bootstrap Method With Better Elements Representation For Univariate Time Series Data

 Kayode AYINDE, James DANIEL, Akinola ADEPETUN And Olusegun S. EWEMOOJE

 2023

Bootstrap method was initially used to determine accuracy measures for sample estimates of independent and identical distributions (i.i.d.). In order to apply bootstrap method to time-dependent data, blocking technique is introduced to preserve serial correlation of the original time series data. In the past, resampling techniques for time-dependent data were implemented using Non-overlapping Block Bootstrap (NBB) method but its dichotomous block arrangement restricts the number of blocks. As a result, improvement becomes necessary. Although the Moving Block Bootstrap (MBB) method improves upon NBB with regard to many more blocks, it introduces an uneven representation of the time series elements which eventually influences its accuracy. In this paper, an innovative method called Moving Block Bootstrap Method with better element Representation (MBBR) is developed to ensure that the time series elements within the block are better represented with minimum number of elements. To compare MBB and MBBR, simulated studies were carried out on some set time series data following each classes of Autoregressive Moving Average (ARMA) model with different parameters, sample sizes and standard deviation using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Results show that by improving the representation of time series data in the blocking arrangement, the accuracy of the proposed method (MBBR) consistently outperforms the existing one (MBB) and thus, provides more efficient estimates of the dependent variable. 

 Kuwait University

 Journal

 Bayesian Estimation Of Warner’s Randomized Response Technique With Transmuted Kumaraswamy Prior

 A. O. Adepetun, B. M. Oseni & O. S. Makinde

 2022

In recent times, the Bayesian approach to randomized response technique has been used for estimating the population proportion, especially of respondents possessing sensitive attributes such as induced abortion, tax evasion, and shoplifting. This is done by combining suitable prior information about an unknown parameter of the population with the sample information for the estimation of the unknown parameter. In this study, the possibility of using a transmuted Kumaraswamy prior is raised, yielding a new Bayes estimator for estimating the population proportion of sensitive attributes for Warner’s randomized response technique. Consequently, the proposed Bayes estimator with transmuted Kumaraswamy prior is compared with existing Bayes estimators developed with a simple beta and Kumaraswamy priors in terms of their mean square error. The proposed estimator competes well with the existing estimators for some values of population proportion ?. The performances of Bayes estimators were also compared using some benchmark data. 

 Kebbi State University Of Science And Technology

 Journal

 A Survey On Reliability Of Smartphones Among Undergraduate Students Based On Brands

 A. O. Adepetun & O. T. Adebayo

 2022

As universities gradually embrace on mobile learning, smartphone usage among undergraduate students in Nigeria has rapidly increased. Smartphones are now used by students for accessing academic information, entering school media sites and performing other academic activities. In this study, a survey on reliability of five different brands of smartphones among undergraduate students of Federal University of Technology, Akure was carried out using well-structured survey questionnaires to gather primary data for the study. Cronbach’s Alpha test was used to validate the acceptable reliability of the survey questionnaire at various level of significance ? while Kruskal – Wallis test was used to test if there was a significant difference in the reliability of these brands of smartphones usage among undergraduate students. In addition, exponential distribution was applied to determine mean time between failure, failure rate, failure density function, and reliability function respectively. Results of the study showed that reliability of smartphones among undergraduates is dependent on the smartphone brand. In particular, it also shows that Samsung smartphone brand is most reliable among the sampled undergraduate smartphone users compared with the other brands since it has the least failure rate and greatest reliability function values within the period of 3 years of purchase considered. 

 Kuwait University

 Journal

 Bayesian Estimation Of Warner’s Randomized Response Technique With Transmuted Kumaraswamy Prior

 A. O. Adepetun , B. M. Oseni & O. S. Makinde

 2022

In recent times, the Bayesian approach to randomized response technique has been used for estimating the population proportion, especially of respondents possessing sensitive attributes such as induced abortion, tax evasion, and shoplifting. This is done by combining suitable prior information about an unknown parameter of the population with the sample information for the estimation of the unknown parameter. In this study, the possibility of using a transmuted Kumaraswamy prior is raised, yielding a new Bayes estimator for estimating the population proportion of sensitive attributes for Warner’s randomized response technique. Consequently, the proposed Bayes estimator with transmuted Kumaraswamy prior is compared with existing Bayes estimators developed with a simple beta and Kumaraswamy priors in terms of their mean square error. The proposed estimator competes well with the existing estimators for some values of population proportion ?. The performances of Bayes estimators were also compared using some benchmark data. 

 Elsevier

 Journal

 The Significance Of Daily Incidence And Mortality Cases Due To COVID-19 In Some African Countries

 O. S. Makinde, B. M. Oseni, A. O. Adepetun , O. O. Olusola-Makinde & G. J. Abiodun

 2021

With the current outbreak of COVID-19, African countries have been on heightened alert to detect and isolate any imported and locally transmitted cases of the disease. It was observed that each of the daily COVID-19 incidence and mortality counts among African countries may not be independent. Result of the Ljung-Box test showed that each of the daily COVID-19 incidence and mortality counts among African countries was not independent, rather both are time-dependent. Analyzing daily COVID-19 incidence and mortality counts over time require more specialized analytic tools. Trend analysis of daily counts of COVID-19 incidence and deaths are presented over time. Also, generalized estimating equation (GEE), a flexible tool for analyzing longitudinal data, is employed to analyze the daily COVID-19 mortality rates in African countries. Findings from this study showed that patterns of incidence cases among African countries are statistically different. There are significant monotone trend in the daily COVID-19 incidence and mortality counts of many countries in Africa. There is a positive weak linear relationship between the daily reported COVID-19 cases and the population of African countries. However, the magnitude of the observed association was particularly small. It was further deduced that the farther the number of days from the day of first incidence if the pandemic is not properly managed, the more the daily COVID-19 mortality rate in Africa. 

 Faculty Of Sciences And Technology, University Of El Oued, Algeria.

 Journal

 Application Of Randomized Response Technique On A Survey Sampling Of Yeast Infection Among Nigerian Female Undergraduates

 A. O. Adepetun

 2020

In this paper, randomized response technique was adopted to determine the proportion of female undergraduates at the Federal University of Technology Akure that have had yeast infection at a point in time, the age range that has the most number of yeast infection cases as well as the female hostel with the highest number of yeast infection cases. Questionnaires were used to collect data from the respondents. Z-tests were used in hypothesis testing. All comparisons involving randomized response data used the estimated proportion of girls with yeast infection and the sampling variance to calculate the z-score. The results of the study indicated that Jadesola female hostel has the most number of yeast infection cases proportion 99.8% while the proportion of yeast infection cases in Jibowu hostel is 66.8%. The result also shows that 90% of the female undergraduates between the age range of 16 and 18 years contracted the infection. 

 Taylor & Francis, United Kingdom

 Journal

 Modeling The Gross Domestic Product Of Nigeria From 1985 To 2018

 Olusola Samuel Makinde, Akinola Oladiran Adepetun & Bamidele Mustapha Oseni

 2020

Gross domestic products (GDP) can be viewed as an internationally accepted measure of economy size and strength. Recent studies have described the relationship between economic growth in terms of GDP and income, decline in mortality and improved health outcomes of some countries. In this paper, stochastic models based on autoregressive integrated moving average (ARIMA (p, d, q)) models of various orders are presented, with a view to identifying the optimal model for the GDP of Nigeria. ARIMA (p, d, q) models are formulated forGDPfromsome economic components and Nigerian overall GDP on a yearly basis. The choice of ARIMA models of orders p and q is intended to retain any persistence in natural process. Observed data are compared with the fitted data using the optimal models. The result shows that the GDP from agriculture, industries, trade and services show statistically significant increasing trends (p value 

 Faculty Of Sciences And Technology, University Of El Oued, Algeria

 Journal

 Contraceptive Usage Among Undergraduate Female Students: A Survey Sampling Approach

 Akinola Oladiran Adepetun

 2020

In this paper, a survey sampling on contraceptive usage among the female undergraduates of Federal University of Technology, Akure using the randomized response technique proposed by Warner [1] was extensively carried out. The data for the study was obtained from the administration of well-structured survey questionnaires on respondents from three different schools in the University. Consequently, the estimated Warner’s proportions of female undergraduate students who used contraceptives and their resulting variances were evaluated at varying sample sizes and predetermined probabilities respectively. The results as presented in the summary table 10 revealed that contraceptive usage was at maximum level for School of Agriculture and Agricultural Technology as sample sizes varied.