http://rulrepository.ru.ac.bd/handle/123456789/79 2026-04-07T21:44:54Z 2026-04-07T21:44:54Z Kundu, Ranjan Kumar http://rulrepository.ru.ac.bd/handle/123456789/1108 2023-08-29T08:06:32Z 2021-01-01T00:00:00Z

Factors Affecting The Technical Efficiency Of Boro Rice Producers Of Northern Rigion In Bangladesh Kundu, Ranjan Kumar Because of its significant contribution to the development of various economic-related activities and self-sufficiency in food production, agricultural production needs to increase under the existing challenges so far. Despite increased rice production, it is evident that among all varieties, Boro rice is contributing the largest share of Bangladesh as well. The satisfactory contribution in the production of Boro rice has been unearthed for the Northern regions of the country in this respect. As therefore, investigation of determinants of production risk and efficiency and /or inefficiency may have an important role based on the stochastic production framework. According to the objectives, an attempt has been made to examine the contributory impact of the assigned input variables using frontier modelling. Firm-level primary data of 350 Boro farmers have collected from Rangpur, Dinajpur, Bogura, and Natore districts using an appropriate sampling technique and choice of functional form, distributional assumptions of models. Together with different preliminary statistics related to the research, technical efficiency has computed using Stochastic Frontier Modelling for selected Upazilas and districts. Small unit efficiencies have been computed for the eight Upazilas. The Farmers' Performance Indicators on the integrated management in the efficiency ground has been investigated under the Half-Normal assumption of errors of districts as well as the pooled data. This Thesis is Submitted to the Department of Statistics , University of Rajshahi, Rajshahi, Bangladesh for The Degree of Doctor of Philosophy (PhD)

2021-01-01T00:00:00Z Khan, Md. Ashraful Islam http://rulrepository.ru.ac.bd/handle/123456789/1105 2023-08-29T08:05:44Z 2003-01-01T00:00:00Z

The Role of High Leverage Points in Regression Diagnostics Khan, Md. Ashraful Islam In fitting a linear regression model by the least squares’ method, leverage values play a very important role. They often fo1m the basis of regression diagnostics as measures of influential observations in the explanatory variables. Much work has been done on the detection of high leverage values and a good number of diagnostic measures are now available in the literature. But neither of these methods is effective in the identification of high leverage points when multiple high leverage points are present in the data. In our study we proposed a new method for the identification of multiple high leverage points. The usefulness of this newly proposed method is studied under a variety of leverage structures through Monte Carlo simulation experiments. We also investigated the performance of the newly proposed method as a remedy to multi collinearity problem caused by the presence of multiple high leverage points. This Thesis is Submitted to the Department of Statistics, University of Rajshahi, Rajshahi, Bangladesh for The Degree of Master of Philosophy (MPhil)

2003-01-01T00:00:00Z Alam, Md. Jahangir http://rulrepository.ru.ac.bd/handle/123456789/1092 2023-08-29T08:03:52Z 2020-01-01T00:00:00Z

Statistical Modeling for Genome Wide Association Studies Alam, Md. Jahangir Genomics is the study of the whole genome of any living organism along with its environment and it incorporates different elements from genetics (a branch of biology that generally deals with the heredity). Genomics uses “DNA sequencing methods” to generate sequences of genomes using recombinant DNA, and it utilizes Bioinformatics to assemble the sequences of whole genomes and analyze the structure and function of genomes. It differs from 'classical genetics' in that it considers an organism’s full complement of hereditary material, rather than one gene or one gene product at a time. Moreover, genomics focuses on interactions between loci and allele within the genome and other interactions such as epistasis, pleiotropy and heterosis (Figure 1.1). The availability of complete DNA sequences for entire organisms is made easy by the Genomics. Genomics was made possible by both the pioneering work of Fred Sanger and the more recent next-generation sequencing technology. Fred Sanger's group established techniques of sequencing, genome mapping, data storage, and bioinformatics analyses in the 1970s and 1980s. This work paved the way for the human genome project in the 1990s (Bentley et al., 2008) an enormous feat of global collaboration that culminated in the publication of the complete human genome sequence in 2003. Nowadays, next-generation sequence technologies have led to remarkable improvements in the speed, capacity and affordability of genome sequencing. Moreover, advances in bioinformatics have enabled hundreds of life- science databases and projects that provide support for scientific research. Information stored and organized in these databases can easily be searched, compared and analyzed…………. This Thesis is Submitted to the Department of Statistics, University of Rajshahi, Rajshahi, Bangladesh for The Degree of Doctor of Philosophy (PhD)

2020-01-01T00:00:00Z Maniruzzaman, Md. http://rulrepository.ru.ac.bd/handle/123456789/1056 2023-08-08T07:07:29Z 2021-01-01T00:00:00Z

Comparison of Performances of Machine Learning Techniques in Healthcare Data Maniruzzaman, Md. Due to the increasing prevalence of diabetes and cancer, it is an urgent need to develop automated system that helps to detect disease using one of the modern technologies. Nowadays, Machine Learning (ML)-based methods have become very popular as an automatically model building techniques. Despite of the rapid development of theories for computational intelligence, application of ML-based classifiers to diabetes and cancer diagnosis remains a challenging issue. Still these ML-based classifiers did not give a satisfactory accuracy and therfore cannot correctly classify healthcare data like diabetes and cancer patients. Because most of the diabetes and cancer dataset are complex in nature and contains missing values, unusual observations, multi-collinearity problems and so on. In most of the existing research, the researcher did not use feature selection (FS) techniques to identify the risk factors of cancer and diabetes disease. They applied limited classifiers to classify and predict the diabetes and cancer status but they did not tune the hyper parameter of the classifiers, as a result, their accuracy and AUC were low. Thus, an attempt has been made in this study to increase the accuracy of the classifiers in diabetes and cancer data by considering the above factors in ML-based algorithm. The main objective of this study is to comparison the performances of ML-based methods in healthcare data and suggests the best model with better performance compared to the models published in the existing research.----- This Thesis is Submitted to the Department of Statistics , University of Rajshahi, Rajshahi, Bangladesh for The Degree of Master of Philosophy (MPhil)

2021-01-01T00:00:00Z