Open Access Original Research Article

On the Improvement of Multivariate Ratio Method of Estimation in Sample Surveys by Calibration Weightings

Etebong P. Clement

Asian Journal of Probability and Statistics, Page 1-12
DOI: 10.9734/ajpas/2020/v10i130236

The most challenging limitation of the ratio estimation is that of deriving variance estimator that admits more than two auxiliary variables. This paper introduces a new calibration weights that prompt the formulation of a multivariate ratio estimator by the calibration tuning parameter subject to a pooled-calibration constraint. Analytical framework for deriving variance estimator that admits as many auxiliary variables as desired is developed. The efficiency gains of the proposed estimator vis-a-vis the Generalized Regression (GREG) Estimator are studied through simulation. Simulation results proved the dominance of the new proposals over existing ones.

Open Access Original Research Article

Evaluating the Agreement between the Twin-Block Appliance and a New Low-Cost Arch Development Appliance in Changing the Mandibular Length

A. M. Imanthi C. K. Jayathilake, Lakshika S. Nawarathna, S. P. N. P. Nagarathne

Asian Journal of Probability and Statistics, Page 13-24
DOI: 10.9734/ajpas/2020/v10i130237

Aim: The main objective of this study is to compare the development of mandibular length by comparing the effectiveness of a new low-cost arch development appliance in increasing the length of the mandible with the twin block appliance (Twin-B).

Methodology: This analysis was performed on patients who attended the clinic in the Division of Orthodontics, Faculty of Dental Sciences, University of Peradeniya. The sample included 60 subjects treated with Twin-B (n=30) and new low-cost arch development (n=30) appliances and each appliance comprised 15 males and females. Intraclass Correlation Coefficient (ICC) and the Concordance Correlation Coefficient (CCC) were calculated to check the agreement between the two methods. A mixed-effects model was fitted to predict mandibular length, and Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and log-likelihood were used for selecting the best model.

Results: It was observed that the Concordance Correlation Coefficient (CCC) for after treatment as 0.9172 with a (0.8488, 0.9555) 95% confidence interval. Furthermore, it gives a Pearson correlation of 0.9609 and bias correlation factor of 0.9545. ICC values after treatment for both single measures and average measures are 0.9499 and 0.9743 with the 95% confidence intervals (0.8976, 0.9758) and (0.9460, 0.9878) respectively.

Conclusion: Besides, both Twin-B and new low-cost arch development appliances have a better agreement and can be used interchangeably. Therefore, the new low-cost arch development appliance is more suitable as a treatment for malocclusion for Sri Lankan patients as it is less expensive, simpler and, less invasive.

Open Access Original Research Article

On the Estimation of Variance of Calibration Regression Estimators with Multiple Auxiliary Information

Etebong P. Clement

Asian Journal of Probability and Statistics, Page 25-35
DOI: 10.9734/ajpas/2020/v10i130238

This paper introduces the concept of calibration estimators to Statistical Regression Estimation and proposes a multivariate calibration regression (M-REG) estimator of population mean in stratified random sampling. It develops a new approach to variance estimation that is more efficient in estimating populations with multiple auxiliary variables using the principle of analysis of variance (ANOVA). The relative performance of the new variance estimation method with respect to the estimation of variance of the proposed M-REG estimator is compared empirically with a corresponding global variance estimation method. Analysis and evaluation presented, proved the dominance of the suggested new approach to variance estimation.

Open Access Original Research Article

Multiple Linear Regression Approach for Strategic Decisions on Industrial Productivity under Limited Available Budget

Oluwaseun Oluwagbemiga Ojo, David Ifeoluwa Oladapo, Abiola Olufemi Ajayeoba, Basil Olufemi Akinnuli, Temitayo Daniel Omotayo

Asian Journal of Probability and Statistics, Page 36-45
DOI: 10.9734/ajpas/2020/v10i130239

Proper planning and improved productivity is highly desired in industrial settings to optimize the available resources when there is limited resources and to control excessive spending in time of surplus.  Productivity is achievable by good levels of Materials, Time and Labor inputs which needs to be measured scientifically in order to maintain long run profit. This study explored processing data and incorporated Statistical Package for Social Science (SPSS) to find the relationship and predict the response of the available budget with the inputs of Materials, Time and Labor using Olam Cocoa Processing Industry, Nigeria as case study. The analyses were done using Multiple Linear Regression Model developed (i.e. ), it was discovered that the inputs of the selected strategic decisions  collectively affected the response of the available budget with F-value of 88.48 but each of them cannot reduce or increase the amount of budget except for manpower which has 0.069 or 93.1 % significant effect on the available budget. Also, Coefficient of determination established a strong fitness of the relationship between the strategic decisions and the available budget with the value of 0.974 (or 97.4 %). It is recommended that the project manager should subject his decisions making into scientific measures rather than brainstorming so as to increase productivity in the company.

Open Access Review Article

Statistical Modelling of Intensity Modes of Rainfall Using Principal Component Itemization: A Case Study of Kano State

Ibrahim Abubakar Sadiq, Nazir Muhammad Isah

Asian Journal of Probability and Statistics, Page 46-56
DOI: 10.9734/ajpas/2020/v10i130240

Kano State is experiencing greater weather extremes, changes in rainfall patterns, analysis of heat and cold waves, and increasing droughts and floods (Kano meteorological agency). As a result, there is a need for the provision of the necessary weather advisories and early warnings to planners, decision-makers, and operators of the various rainfall-sensitive socio-economic sectors. However, this study is aiming to realize some hidden variables of Kano State total monthly rainfall dataset from the onset to cessation period of rain from the month of April to October over a 105 years (1911-2015) for classification into the intensity of the rain of the area under study, also to determine the linear model for the changing patterns of rainfall in Kano State and to identify some of the adverse impacts on socio-economic sectors and transport infrastructures. Thus, the appearances of the rainfall figure are established for the study region with the operation of Principal Component Analysis (PCA), application least square method. The leading three (3) PCs, gives account for about 61% of the entire disparity, is described. The revision displays and describe PC1 as associated with the heavy intensity rainfall, whereas PC2 is connected to the moderate-intensity rainfall and finally PC3 is linked to the light intensity rainfall of the region under study. By the scores of our PCs, uniform rainfall zones are established over the region of enquiring to which the yearly performance of rainfall is discussed. Statistically, all three models for the various mode of rainfall intensity are significant, which serves as the annual pattern of rainfall in the study area.