Journal of Data Science

In square contingency tables, analysis of agreement between row and column classifications is of interest. For nominal categories, kappa co- efficient is used to summarize the degree of agreement between two raters. Numerous extensions and generalizations of kappa statistics have been pro- posed in the literature. In addition to the kappa coefficient, several authors use agreement in terms of log-linear models. This paper focuses on the approaches to study of interrater agreement for contingency tables with nominal or ordinal categories for multiraters. In this article, we present a detailed overview of agreement studies and illustrate use of the approaches in the evaluation agreement over three numerical examples.

In this article a new Bayesian regression model, called the Bayesian semi-parametric logistic regression model, is introduced. This model generalizes the semi-parametric logistic regression model (SLoRM) and improves its estimation process. The paper considers Bayesian and non-Bayesian estimation and inference for the parametric and semi-parametric logistic regression model with application to credit scoring data under the square error loss function. The paper introduces a new algorithm for estimating the SLoRM parameters using Bayesian theorem in more detail. Finally, the parametric logistic regression model (PLoRM), the SLoRM and the Bayesian SLoRM are used and compared using a real data set.

We introduce a new family of distributions based on a generalized Burr III generator called Modified Burr III G family and study some of its mathematical properties. Its density function can be bell-shaped, left-skewed, right-skewed, bathtub, J or reversed-J. Its hazard rate can be increasing or decreasing, bathtub, upside-down bathtub, J and reversed-J. Some of its special models are presented. We illustrate the importance of the family with two applications to real data sets.

For the purpose of generalizing or extending an existing probability distribution, incorporation of additional parameter to it is very common in the statistical distribution theory and practice. In fact, in most of the times, such extensions provide better fit to the real life situations compared to the existing ones. In this article, we propose and study a two-parameter probability distribution, called quasi xgamma distribution, as an extension or generalization of xgamma distribution (Sen et al. 2016) for modeling lifetime data. Important distributional properties along with survival characteristics and distributions of order statistics are studied in detail. Method of maximum likelihood and method of moments are proposed and described for parameter estimation. A data generation algorithm is proposed supported by a Monte-Carlo simulation study to describe the mean square errors of estimates for different sample sizes. A bladder cancer survival data is used to illustrate the application and suitability of the proposed distribution as a potential survival model.

The surrogate markers(SM) are the important factor for angiogenesis in cancer patients.In Metronomic Chemotherapy (MC) , physicians administer subtoxic doses of chemotherapy (without break) for long periods, to the target tumor angiogenesis. We propose a semiparametric approach, predictive risk modeling and time to control the level of surrogate marker to detect the perfect dose level of MC. It is based on the controlled level of surrogate marker, and the aim is to detect an Optimum Biological Dose (OBD) finding rather than a traditional Maximum Tolerated Dose (MTD) approach. The methods are illustrated with MC trial dataset to determine the best OBD and we investigate the performance of the model through simulation studies.

This paper discusses the coherent forecasting in two types of integervalued geometric autoregressive time series models of order one, viz., Geometric Integer-valued Autoregressive (GINAR(1)) model and New Geometric Integer-valued Autoregressive (NGINAR(1)) model. GINAR(1) model uses binomial thinning for the process generation, whereas, NGINAR(1) uses negative binomial thinning. The k-step ahead conditional probability mass function and the corresponding probability generating functions are derived. It is observed that for higher order lags, the conditional mean, variance and the probability generating functions of these two processes are close to each other, whereas, for lower order lags, they differ. The coherent forecasting performance of these models is studied with the help of simulated and real data sets.

An extension of truncated Poisson distribution having two parameters for a group of two types of population is derived and named as Bounded Poisson (BP) distribution. To estimate the parameters, method of moment has been employed. To check the suitability and applicability of the model it has been applied on real data set on human fertility derived from the third round of National Family Health Survey conducted in 2005-06 in Uttar Pradesh, India. Proposed model provides a good fitting to the data under consideration.