Open Access Original Research Article

Determinants and Management of Patient Waiting Time in the General Outpatient Department in Kibabii University Health Clinic, Kenya

Sevu Muen, Samson W. Wanyonyi, Davis Mwenda Marangu, Obare D. Mong’are

Asian Journal of Probability and Statistics, Page 1-9
DOI: 10.9734/ajpas/2018/v2i428794

The purpose of this paper is to determine the time that a patient can spend waiting for service in Kibabii University Healthcare Clinic in Bungoma County (Kenya). The main objective was to provide necessary information to service facility managers, stakeholders, hospital staffs and other related institutions with the knowledge to improve the queuing system or to curb long waiting time of patients seeking services which can cause deterioration of the disease and sudden demise. This project also aims at providing suggestions to various factors identified to be the causes of long waiting time in the outpatient department at Kibabii University healthcare to help the smooth running of the clinic. The ODK tool was used in data collection procedure to capture the opinions of the respondents. The results from the ODK Tool was exported to XLS which is an export feature of data to excel, later data was exported to SPSS for analysis from excel.

Open Access Original Research Article

Statistical Analysis Based on Lake Michigan Fish Acoustic Data Using LASSO Method

Liming Xie

Asian Journal of Probability and Statistics, Page 1-17
DOI: 10.9734/ajpas/2018/v2i429875

LASSO method is one of the most popular and more extensive regressions. It has been applied to many fields. However, it is rare seen to research with complicated big data in biology. This paper is to apply LASSO method to Lake Michigan Fish acoustic data. The main techniques include: Elastic Net selection, which tests validation from the average square error (ASE) to predict the error for the model by computing separately for each of these subsets; defaulting group LASSO to test multiple parameters by splitting a couple constituent parameters, such as successive intervals, multiple continuous depth layers, to estimate the Schwarz Bayesian information criterion (SBC) to find the lowest value for the model; The adaptive LASSO selection, which is applied to each of the parameters in constructing the LASSO constraint for weights, that is, the response y has mean zero and the regressor x are scaled to have mean zero and common standard deviation. The empirical results show that the fish density (Y) has strong relationships with area backscattering coefficient (PRC_ABC), secondly, significant interactions with PRC_ABC and Exclude below line depth mean), among PRC_ABC, fish density in the intervals and layers of acoustic survey transect of Lake Michigan.

Open Access Original Research Article

Bayesian Estimation of the Scale Parameter of the Weimal Distribution

Tajan Mashingil Mabur, Aisha Omale, Ahmed Lawal, Mustapha Mohammed Dewu, Sa’ad Mohammed

Asian Journal of Probability and Statistics, Page 1-9
DOI: 10.9734/ajpas/2018/v2i429944

This article aims at estimating the scale parameter of the Weimal distribution using Bayesian method and comparing the estimators obtained to the estimator of the scale parameter obtained from the method of maximum likelihood. Under Bayesian approach, the estimators are obtained by using uniform prior and Jeffrey’s prior with the adoption of the precautionary, quadratic and square error loss functions. A derivation and discussion2ws under maximum likelihood estimation is also done. The above methods of estimation employed in this paper are compared based on their mean square errors (MSEs) through a simulation study carried out in R statistical software with different sample sizes. The results indicate that the most appropriate method for the scale parameter is precautionary loss function under either uniform or Jeffrey’s prior irrespective of the sample sizes allocated and the values taken by the other parameters.

Open Access Original Research Article

Unrestricted Vector Autoregressive Modelling of the Interaction among Oil Price, Exchange Rate and Inflation in Nigeria (1981–2017)

G. L. Tuaneh, L. Wiri

Asian Journal of Probability and Statistics, Page 1-19
DOI: 10.9734/ajpas/2018/v2i429946

The interdependence among oil prices, exchange rates and inflation rates, and their response to shocks, was a cause of concern. Unrestricted Vector Autoregression (UVAR) was employed to analyse this interactions as well as to investigate the pattern of causality among the study variable. Annual data spanning from 1981 to 2017 was sourced from the Statistical Bulletin of the Central Bank of Nigeria. Pre-estimation analysis showed that all variables were integrated of order one 1(1), and there no cointegrating relationship. The inverse root of AR characteristic polynomial showed a stable VAR model. All lag length selection criteria chose a lag length of 1. The UVAR estimates and the test of significance particularly the granger causality test indicated significant influence and uni-directional effect from oil price to exchange rates. The Wald statistics, showed significant own shocks, and the impulse response showed that all variables were instantaneously affected by own shocks. Exchange rate was instantaneously affected by oil price; however, it ruled out the response in inflation rate to contemporaneous shocks in oil price. The variance decomposition further showed that at least 93.1%, 97.1% and 92.4% of the impulse response in oil price, exchange rate, and inflation rate respectively were from own shocks in the long run. The post estimation analysis showed that the VAR model was multivariate normal, the residual was homoscedastic, and there was no serial autocorrelation. It was recommended that the government should diversify the national income stream and consider policies that will control inflation.

Open Access Original Research Article

An Extended Pranav Distribution

O. R. Uwaeme, N. P. Akpan, U. C. Orumie

Asian Journal of Probability and Statistics, Page 1-15
DOI: 10.9734/ajpas/2018/v2i430078

In this study, we proposed a generalization of the Pranav distribution by Shukla (2018). This new distribution called an extended Pranav distribution is obtained using the exponentiation method. The statistical characteristics of this new distribution such as the moments, moment generating function, reliability function, hazard function, Rényi entropy and order statistics are derived. The graphical illustrations of the shapes of the probability density function, the cumulative distribution function, and hazard rate functions are provided. The maximum likelihood estimates of the parameters were obtained and finally, we examine the performance of this new distribution using some real-life data sets to show its flexibility and better goodness of fit as compared with other distributions.