Journal of the Kerala Statistical Association https://ojs.ksa.org.in/index.php/JKSA <p>Journal of the Kerala Statistical Association is the official peer-reviewed Journal of Kerala Statistical Association (KSA) founded in 1978. The Journal has been published since 1980 and is published annually. The Journal is intended to publish papers that make significant original contributions in both theory and methodological advances in Probability and Statistics. New applications of statistical and probabilistic methods will also be considered for publication. The Journal is open to critical debate in the objective, wide-ranging and free spirit of research. The international editorial board of the Journal is comprised of scientists with interests in applied, computational, methodological and theoretical aspects of Probability and Statistics. </p> <p>The editorial history of the journal includes, Prof K Ramakrishna Pillai (St. Thomas College Pala), Prof R N Pillai (University of Kerala), Prof P Yageen Thomas (University of Kerala) and currently Prof K Jayakumar (University of Calicut) as Journal editors. The journal has already published 32 volume and cumulatively more than 100 research papers.</p> <p> </p> <p><strong>Aim of the Journal:</strong> The Journal’s emphasis is on publishing papers developing and analyzing new methods for any active field of statistics and probability theory with direct or potential real-life applications. The Journal seeks papers making significant contributions of interest to a broad group of readers than to a highly specialized group. Original contributions in the interface of statistics and other fields are also published.</p> KSA en-US Journal of the Kerala Statistical Association 2249-4553 A General Method of Construction of a Bivariate Lifetime Distribution with a Singular Component https://ojs.ksa.org.in/index.php/JKSA/article/view/31 <p>Marshall-Olkin bivariate exponential distribution is the most popular bivariate distribution with a singular component. Since then several other bivariate distributions with a singular component have been introduced in the literature. It is observed that there are mainly two main approaches to construct a bivariate distribution with a singular component. In this paper we have proposed a general method to construct a bivariate distribution with a singular component. All the existing bivariate distributions with a singular component can be obtained using this method. Moreover, more flexible bivariate distributions with a singular component also can be constructed using this method. It is a very simple procedure based on mixing. Using this approach, we have considered one special case, namely bivariate Weibull distribution, in detail. We have derived several properties of the proposed bivariate Weibull distribution and it seems to be more flexible than the popular Marshall-Olkin bivariate Weibull distribution. Maximum likelihood estimators can be obtained quite conveniently in this case. It can be used to model dependent competing risks data and it can be generalized to the multivariate set up also.</p> Debasis Kundu Copyright (c) 2022 Journal of the Kerala Statistical Association 2020-12-01 2020-12-01 31 1 1 28 Generalized Lehmann Alternative Type II Family of Distributions and Their Applications https://ojs.ksa.org.in/index.php/JKSA/article/view/32 <p>A new generalized family called Generalized Lehmann Alternative Type II (GLA2) family is introduced and studied in this paper. Special cases of this family using Uniform and Kumaraswamy distributions as base are developed and their statistical properties studied. Generalized Lehmann Alternative Type II Exponential (GLA2E) distribution is also developed and its statistical properties are obtained along with application. The new distribution is applied to a real data set to show the effectiveness of the distribution and it is verified that the new model is a better model than the existing exponential model and Marshall-Olkin extended exponential model. A detailed study on the record value theory associated with GLA2E distribution is conducted. Using the mean, variance and covariance of upper record values of the extended model, BLUE’s of location and scale parameters are obtained and future records are predicted which has a number of practical uses. The 95% confidence interval for location and scale parameters are also computed. The result is applied to a real data set to validate the results. Entropy of record values is derived. This result will be useful in characterization of record values based on entropies and a quantification of information contained in each additional record value based on entropy measure.</p> Jisha Varghese E Krishna K K Jose Copyright (c) 2022 Journal of the Kerala Statistical Association 2020-12-01 2020-12-01 31 1 29 67 Comparison of Machine Learning Techniques for Recommender Systems for Financial Data https://ojs.ksa.org.in/index.php/JKSA/article/view/33 <p>Recommender Systems are one of the most successful and widespread application of machine learning technologies in business. These are the software tools used to give suggestions to users on the basis of their requirements. Increase in number of options: be it number of online websites or number of products, it has become difficult for the customer to choose from a wide range of products. Today there is no system available for banks to provide financial advisory services to the customers and offer them relevant products as per their preference before they approach the bank. Like any other industries, financial service rarely has any like, feedback and browsing history to record ratings of services. So it becomes a challenge to build recommender systems for financial services. In this research paper, authors propose a collaborative filtering technique to recommend various products to the customer in order to increase the product per customer (PPC) ratio of bank. The advantage of these recommender systems is that it provides better suggestion to the customer based on his needs/requirements for his/her savings, expenditure and investments.</p> Divya G Nair K Muralidharan Copyright (c) 2022 Journal of the Kerala Statistical Association 2020-12-01 2020-12-01 31 1 68 84 Measure of Slope Rotatability for Second Order Response Surface Designs Under Tri-Diagonal Correlation Error Structure Using Central Composite Designs https://ojs.ksa.org.in/index.php/JKSA/article/view/34 <p>In the design of experiments for estimating the slope of the response surface, slope rotatability is a desirable property. In this paper, measure of slope rotatability for second order response surface designs using central composite designs under tri-diagonal correlation error structure is suggested and illustrated with examples.</p> B Sulochana Victorbabu B Re Copyright (c) 2022 Journal of the Kerala Statistical Association 2020-12-01 2020-12-01 31 1 85 104