Department of Statistics

Permanent URI for this community

https://keffi.nsuk.edu.ng/handle/20.500.14448/3878

Browse

Browsing Department of Statistics by Author "Adehi, Mary Unekwu"

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemOpen Access
    Analysis of the Effects of Climate Change on Jamila Rice Output in Kaduna-Nigeria
    (Department of Statistics, Nasarawa Sate University Keffi., 2018-01-01) Adehi, Mary Unekwu; Nweze, N.O.; Chaku, Shammah Emmanuel
    The effect of climate change factors and non- climate change factors on Jamila Rice output have been investigated, using secondary sources of time series annual data obtained from Zaria and Rumi area of Kaduna State for the period of 1980-2013. The error correction mechanism was analyzed, and it was shown that in the short run, only rainfall tested significantly positive to rice output among the climate change factors. In the long run, temperature, carbon dioxide emission, carbon emission and rainfall tested significantly to rice output. There is a need to formulate policies that will aid farmers towards adaptation practices to mitigate the effects of climate change and motivate them to increase their involvement in rice production.
  • Thumbnail Image
    ItemOpen Access
    CAPACITY DEVELOPMENT 4.0 AS A STRATEGY TOWARDS SUSTAINABLE DEVELOPMENT GOALS AND EFFECTIVE NATIONAL STATISTICAL SYSTEMS
    (Department of Statistics, Nasarawa Sate University Keffi., 2017-09-08) Adehi, Mary Unekwu; Chaku, Shammah Emmanuel; Maijamaa, Bilkisu
    The paper examines a shift from focusing on the Millennium Development Goals (MDGs) to focusing on the Sustainable Development Goals (SDGs), the implications for developing countries, and the support that Capacity Development 4.0 (CD 4.0) could provide to BIG data. CD 4.0 reflects on the political economy of main stakeholders. Past policies show that there is a clear need for outside support of data ecosystems in developing regions. However, some constraining factors prevent this. They include, the existence of limited incentives to invest in data ecosystems by development co-operation providers. Also, the lack of government support for the idea of a high-quality and transparent data ecosystem in some developing countries. These constraints are catered for in CD 4.0. The paper considers areas that developing nations might prioritize and how these could contribute to the broader follow-up and review frame work proposed by PARIS21 strategy towards effective use of bigger and better data for better policies and ultimately better lives.
  • Thumbnail Image
    ItemOpen Access
    COVID-19, LEARNING & DIVIDENDS
    (Department of Statistics, Nasarawa State University Keffi., 2020-05-30) Adehi, Mary Unekwu; Maijamaa, Bilkisu
    The era of coronavirus pandemic (November 2019 to June 2020) has been a traumatic period for all countries around the globe. It was a very sober period because the virus is a novel one, and mortality and infection rates were on very rapid increase while scientists battled with treatment measures as well as vaccine discoveries to quell the pandemonium. The home front and life style in general changed, while the big question is, was there a benefit? People generally embraced virtual meetings to be able to interact and move on with life. The 16 Plus school in Lagos Nigeria was not left out of these meetings, as such, during one of such virtual meetings for the end of semester assembly, 30th May, 2020, we presented this paper to 65 members of staff, 10 parents and 25 graduating students (age 16 and above) with an objective to identify some benefits of the pandemic period. Some methods that were adopted to extract information for this paper include google search of periodicals. It is really nice to note that despite all odds, ‘lemonades were made from lemons’ in covid-19 era.
  • Thumbnail Image
    ItemOpen Access
    Modeling Of Species Interaction in a Habitat Using Lotka- Volterra Type Systems
    (Department of Statistics, Nasarawa Sate University Keffi., 2018-01-01) Nweze, N.O.; Offiong, N.M.; Adehi, Mary Unekwu; Chaku, Shammah Emmanuel; Abdullahi, A.S.; Muhammad, Mahammad N.
    Mathematical models have been useful in the area of modeling of real life situations; its application can be found in virtually all spheres of scientific researches. As such, we adopt its use in the field of ecology where preys have to compete with other prey for survival. In this paper, we considered Lotka-Volterra type systems, consisting of two first order differential equations which were used to model the population size of prey–predator interaction. We also proposed a system of first order differential equations to model the population sizes of a prey and two predators. Under these conditions one of the predators dies out while the remaining predator and prey approach periodic behavior as time increases. Also we model the population size of two preys and one predator where there may be interaction between the preys. Under these conditions we found that one of the preys died out while the remaining preys and predators approached periodic behavior as time increased. For critical cases, each positive solution of the system was seen to be periodic in nature. Various examples and results were presented and further study was proposed.
  • Thumbnail Image
    ItemOpen Access
    MODELLING CLAIM FREQUENCY AND LOSS DUE TO CLAIMS OF AUTOMOBILE INSURANCE
    (Depatment of Statistics, Nasarawa State University Keffi, 2017-01-05) Chaku, Shammah Emmanuel; Nwankwo, Chike Henry; Adehi, Mary Unekwu
    The purpose of this study is to model the claim frequency and loss due to claims of automobile insurance. The Poisson, Gamma and their offset termed regression models were applied on the motor insurance data as compiled by the Swedish committee on the analysis of risk premium. Using the Generalised Linear Models (GLM), the applied models were diagnosed and the results of the application was obtained, analysed and the better model identified. The fitted models were further used to carry out predictions of claim frequency and severity (loss due to claims), where the offset termed Poisson model was seen to predict closer than the normal Poisson model. For the prediction of loss due to claims (payments), the Gamma model without the offset term is seen to perform better.
  • Thumbnail Image
    ItemOpen Access
    On Survival of Hiv Patients Using Share Frailty Model
    (Department of Statistics, Nasarawa State University Keffi., 2016-04-19) Maijamaa, Bilkisu; Chaku, Shammah Emmanuel; Adehi, Mary Unekwu; Modu, Babagana
    In a situation of terminal event of death happening during follow-up period to preclude further occurrence for recurrent event, the shared frailty model is used considering proportional hazard model for the recurrent and terminal process. Covariates effect taken into account are the ART status of entry, number of medication taken and CD4PepBase of the HIV patient and dependence modeled by the shared frailty model on survival. Human immunodeficiency virus has now reduced from a fatal disease to a chronic disease due to a high rate of antiretroviral treatment ART. ART helps in reducing the viral load and hence bringing mortality due to HIV/AIDS to the lowest minimum. Factors associated with mortality in HIV has significantly studied in the most literature, less attention given to the stages of HIV at which the ART began about the survival time. The awareness and risk factors for mortality at each stage of HIV on when the ART starts for a subject considered in this paper. The research aimed at constructing appropriate measures on stages at which the ART is started to the survival time is evaluated using a shared frailty model to account for heterogeneity within groups of stages of HIV subject.
  • Thumbnail Image
    ItemOpen Access
    Time Series Modeling and Forecasting of Gold Prices on International Financial Markets
    (Department of Statistics, Nasarawa Sate University Keffi., 2020-07-05) Chaku, Shammah Emmanuel; Gabriel, F.G.; Abdulrazaq, A.A.; Adehi, Mary Unekwu; Timnan, B.N.
    Application of SARIMA model in modeling and forecasting average monthly gold prices was carried out in this study. Data on gold from January 2015 to December 2020 was obtained. Monthly adjusted close prices were used for the analysis. The gold price data was stationary after first difference (D = -3.8426, P = 0.02183< 0.05). SARIMA(0,0,0)(0,1,1)[12] was identified as the best model that fit the gold price data with minimum AIC and BIC. Forecast of gold prices from January, 2021 to December 2025 was obtained. Forecast shows a rise and fall of the average monthly gold price over the forecast period (2021-2025). The Forecast values were tested against actual values for January, 2021 to June, 2021. There was no significant difference between the actual gold prices against predicted values (t = 2.102, P = 0.07191< 0.05). Prospective investors should consider gold in their portfolios as a store of value and a diversification tool and cautious of the price fluctuation predicted in this study.