Asian Journal of Probability and Statistics

The incurable lingering metabolic syndrome of diabetes mellitus is an up-surging global tricky with tremendous physical, social, mental, economics and health undesired ramifications. Three hundred and ninety four diabetic patients were measured on 4 baseline variable age (years), sex (Male=1 and Female=2), body mass index (kg/m²) and blood pressure (mmHg). Blood sugar concentration (mg/dl) represented the response variable. The basic objective of this study is to verify the clear causal risk factors of diabetes. Both Multiple Linear Regression and Stepwise Regression techniques were applied on the data and the analysis showed that Body Mass Index (kg/m²) and Blood Pressure (mmHg) are the clearest risk factors of diabetes. This justification served the same purpose in the procedure of variables selection used.

In this paper, we introduced the Inverted Power Rama distribution as an extension of the Inverted Rama distribution. This new distribution is capable of modeling real life data with upside down bathtub shape and heavy tails. Mathematical and statistical characteristics such as the quantile function, mode, moments and moment generating function, entropy measure, stochastic ordering and distribution of order statistics have been derived. Furthermore, reliability measures like survival function, hazard function and odds function have been derived. The method of maximum likelihood was used for estimating the parameters of the distribution. To demonstrate the applicability of the distribution, a numerical example was given. Based on the results, the proposed distribution performed better than the competing distributions.

This paper is an attempt to solve singular value problems for higher order ordinary differential equation by using new modification of Adomian Decomposition Method (ADM). Convergent series solution of considered problem have been obtained. Three numerical examples are discussed to validate the strength and ease of the method used.

A new generator of continuous distributions called the Inverse Lomax-Exponentiated G family, which has three extra positive parameters is proposed. The structural properties of the new family that holds for any continuous baseline model including explicit density function expressions, moments, inequality measurements, moment generating function, reliability functions, Renyi and Shanon entropies, and distribution of order statistics are derived. A Monte Carlo simulation to test the efficiency of the maximum likelihood estimates is conducted. The application of the new sub-model to the two data sets using the maximum likelihood method indicates that the new model is better than the existing competitors.

This paper convolutes two generalized distributions from the family of generated T - X distribution. The new distribution generated from these distributions is called the Generalized Weibull-generalized Exponential Distribution. The properties of the proposed distribution are derived. Method of maximum likelihood estimation is used to estimate the parameters of the distribution and the information matrix is obtained. Thereafter, the distribution is applied to a real life dataset of failure for the air conditioning system and the obtained results are compared with other existing distributions to illustrate the capability and flexibility of the new distribution.