Statistics

In this paper, we propose a new optional randomized response model based on Gupta and Shabbir (2007) two-stage randomized response model which unbound the assumption that the mean of the scrambling variable S is ‘unity’ [i.e. ]. We derive the estimator of the sensitive variable, mean, and show that our method is more efficient than other randomized response models suggested by Eichhorn and Hayre (1983) and Gupta and shabbir (2007) estimators. A numerical illustration is given in support of the present study.

Anaemia is a common health problem among women throughout the world. The present study with the objective to assess the nutritional status of rural village women and to study the knowledge of village women regarding Anaemia. In addition to this, the effect of various socio-economic and demographic factors on Anaemia related knowledge of village women are assessed. The cross sectional study was carried out in Punavasal village of Tiruvarur District in Cauvery delta region, Tamil Nadu. A total of 1000 respondents were selected randomly. Their knowledge was tested and socio-demographic and nutritional profile was recorded. Conclusion was that knowledge of rural women was found to be very poor in regard of Anaemia, nutritional status was unsatisfactory. To eradicate the problem of Anaemia a more intense awareness campaign is required in the region. Keywords: Anaemia, Heamoglobin, Blood, RBC, WBC.

Child mortality refers to the death of infants and children under the age of five or between the age of one month to four years depending on the definition. Child mortality is a core indicator of child health and well-being. In this paper we propose a probability model for child mortality among women with fixed parity under certain assumption and techniques. The suitability of the model is tested through observed data. NFHS-3 data has been used to carry out this study.

This study was carried out to examine survey responses across various levels of response predictors in some selected communities in oyo town, Oyo State, Nigeria. The design for this study was a two-stage stratified random sampling scheme. A Sample of 750 households was randomly selected in fifteen Enumeration Areas in Oyo town. The data were collected by interviewer-administered questionnaire and predictors of response were extracted for the verification of response rates at various levels of these predictors. Out of the 750 respondents that were interviewed in each of the five waves, 545, 615, 610, 615, 605 responded to survey questions respectively. The maximum number of visits considered for this research work is five per wave and after the fifth visits, respondents were regarded as non response. The response rates from the following predictors:- Females, those that were living with their spouse, those that were interviewed with English language, respondents at the middle age (50-79 years), those that are familiar with the interviewer and tenants were observed to be high. Also, the response rates increases from first visit to the fourth visits and at the fifth visit, it declined. We also observed that the more the number of years a respondent has spent in his/her community, the more they response to survey questions.

In this paper, we have considered the problem of estimating the population mean of study character using mean square error by double sampling the non-respondents. Two generalized estimators for estimating the population mean using auxiliary character under two different cases are proposed. Further the problem has been extended to the wider classes of estimators, which include several generalized estimators as a particular member. The bias, mean square error and optimum property of the proposed classes of estimators have been obtained under different cases. The efficiency of the proposed classes of estimators has also been shown through the theoretical and empirical studies. 

Moderated mediation has been proven to be one of the useful techniques in providing powerful analysis in many research areas such as social science, statistics, marketing, health science and others. By using secondary data obtained from Trends In Mathematics and Science Study (TIMSS), moderated mediation analysis is used to determine the significance difference of direct effect and total effect including indirect effect of exogenous latent constructs toward endogenous latent construct through mediator latent construct between moderator; male and female samples. From the Moderation Analysis, it is found that there is no significant difference between male and female samples in the direct effect of all exogenous latent constructs toward endogenous latent construct. The same result obtained in Moderated Mediation Analysis where there is no significant difference between male and female samples in the total effect including indirect effect from all exogenous latent constructs toward endogenous latent construct through mediator latent construct.

Child care has become an essential component of life in our society .Quality child care can make a significant difference in child’s development .Here we consider some regulations in favour of lower child staff ratio ,higher educational standards for care givers and smaller group size . In this paper we present a methods for fuzzy risk analysis based on, child- staff ratio group size and care giver ability. We obtain the expected number of children in queue needing attention at any time by using both function principle and Graded Mean Integration method. Furthermore we calculate the proportion of time that a child would spend engaged by using both function principle and Graded Mean Integration method. The model presented in this paper can be applied to other educational services also

The study of stochastic phenomena has increased dramatically and intensified research activity in this area has been stimulated by the need to take into account random effects in complicated dynamical systems. Dynamical systems are ubiquitous and are considered to be stochastic processes. In this study, a nonlinear dynamical system was modeled as a solution to an Ito stochastic differential equation . Where denotes a Wiener or Brownian motion process while and are deterministic functions. The Ito Stochastic Differential Equation was applied to characterize the important functional of the solution process in some intervals [0,t],X(t) which satisfies the integral equation, X(t)=X(0)+?_0^t??f(s,X(s))ds?+?_0^t??g(s,X(s) )dW(s)?. The solution of the integral equation is a Lagenvin equation which is an Ornstein-Uhlenbeck (O-U) process dX_t=?(?-X_t )dt+?dW_t. The O-U process which is a Gaussian process was related to the world of time series analysis. The model was applied to Nigerian monetary exchange rate and compared with the existing models of monetary exchange rate. R package and the Akaike Information Criteria (AIC) were used to provide the model of best fit for the Nigerian monetary exchange rate as an autoregressive moving average of order one which is given to be? S?_t=0.4287S_(t-1)+?0.2099e?_(t-1)+e_t. The results obtained revealed that the structural diffusion model approach gives a first-order autoregressive moving average process in continuous time with differentiation in continuous time corresponding to differencing in discrete time. The derived structural diffusion model has the least AIC value of 1482.61 as compared to the AIC value of 2198.86 from the existing diffusion and normal models. Keywords: Nonlinear Model, Dynamical System, Diffusion Model,

This work examined the efficiencies of Ordinary Least Squares (OLS) and Seemingly Unrelated Regression (SUR) estimators in lagged and unlagged models. Literature has shown gain in efficiency of SUR estimator over OLS estimator when the errors are correlated across equations. This paper studied the efficiencies of these estimators in a lagged and unlagged models and also sought a comparative study of these estimators in both models.Data was simulated for sample sizes 50, 100 and 1000 with 5000 bootstrapped replicates in each case with the predictors having Gaussian distribution. Results from the study showed that both estimators were efficient in each model with the SUR estimator being consistently more efficient than the OLS estimator as the sample size increased. On the assessment of the models, the unlagged model was found to be more efficient than the lagged model in small sample but converged as sample size increased.

Nigeria is classified as a mixed economy emerging market, and has already reached middle income status according to the World Bank, with its abundant supply of natural resource, well developed financial, legal, communications, transport sectors and stock exchange which is the second largest in Africa. The main purpose of this research is to build a model that can capture the best variables that predict the Gross Domestic Product (GDP) of Nigeria. Correlation matrix was used to know the degree of relationship that exists between the pairs of predictors of GDP. The principal component analysis was employed to reduce the multidimensional data. Scree plot was used to determine the spread of the trend of the components and bi plot was used to determine the degree of closeness of Agriculture, oil Export, External Reserves, Exchange Rate, Transportation, Education, and Communication. There is a strong relationship between pairs of Agriculture, oil Export, External Reserves, Exchange Rate, Transportation, Education, and Communication. The proportion of variance accounted for by the first component is 92%. This implied that only component 1 is sufficient to explain GDP. The Scree plot showed that the best component is component 1. The bi plot showed that Agriculture, oil Export, External.Reserves, Exchange.Rate, Transportation, Education, and Communication are closely related and stand as good predictors of GDP. Keyword: Gross Domestic Product, Principal Components, Bi plot, Scree plot