Journal of Statistical Modeling & Analytics (JOSMA)

Formulating of Linear Model from One-Way Classification Model

2024-10-02T14:40:42+08:00

This study introduces a novel approach to formulating a linear regression model using a matrix method for Completely Randomized Design (CRD), a type of One-Way classification. In this approach, treatment is the sole classification, and the formulation utilizes response variables organized into rows and columns. The method yields the number of trials (n), slope, predictor, and regression parameters within the system. To ensure the normality of the response variable and select the appropriate error term distribution, we conducted normality tests (Shapiro-Wilk, Anderson-Darling, Cramér-von Mises, Lilliefors) and exploratory data analysis techniques (histogram, boxplot, QQ-plot). The formulation was validated through illustrations, and the results from the matrix method regression were compared to the ordinary least squares regression, yielding identical values for the regressors, and confirming the robustness of the proposed formulation. Furthermore, we evaluated the performance of machine learning linear regression model, which outperformed ordinary least squares regression in terms of mean absolute error, mean square error, and root mean square error, demonstrating the superior accuracy of the proposed approach.

Enhancing Diabetes Mellitus Onset Prediction through Advanced Ensemble Learning Techniques

2024-11-11T15:43:45+08:00

Type 2 diabetes is a major worldwide health issue, necessitating accurate and effective prediction models for timely intervention. Traditional machine learning (ML) models often underperform with imbalanced datasets and complex data relationships, resulting in suboptimal predictive accuracy. This study applies advanced ensemble methods, such as random forest, boosting, bagging, and stacking, to enhance diabetes onset prediction using a synthetic minority over-sampling technique (SMOTE)-balanced data from the Pima Indians Diabetes Database. The research involves extensive data processing, feature engineering, and cross-validation. Model performance is assessed using several evaluation metrics, such as F1-score and AUC-ROC (Area Under the Curve-Receiver Operating Characteristic), along with accuracy, precision, and recall. The findings indicate that ensemble techniques, especially random forest, bagging, and boosting, surpass traditional models, achieving an accuracy of 88%, recall of 82%, and precision of 85%. These findings emphasize the effectiveness of ensemble learning in enhancing predictive analytics for healthcare, supporting early diagnosis, and personalized patient care. Future research should explore integrating deep learning models with diverse datasets to improve predictive accuracy and generalizability.

Malaysia’s Development Expenditure Effects on Gross Domestic Product by Using VECM Approach

2024-11-11T15:47:23+08:00

The provision of public goods and services to citizens is a significant responsibility of the government. The products include schools, hospitals, roads, and other infrastructure. This investment is essential to stimulate economic growth, create job opportunities, and improve living standards. The effect of development spending on economic growth has been shown in a significant amount of existing literature. However, there are still various opinions on the impact level of development spending on economic growth. Therefore, the goal of our research is to investigate the link between Malaysia's Gross Domestic Product (GDP) and Development Expenditure (DE) based on the long-run and short-run vector error correction model (VECM) approach. The findings show that the long-term impact of GDP on development spending is positive, according to the results of the Johansen co-integration test. The long-run VECM also shows a positive correlation between GDP and government spending on development. Development spending and lag one GDP are negatively correlated. The short-run VECM shows a positive correlation between GDP and GDP lag. Unrestricted Vector Autoregressive (VAR) demonstrates that government spending on development has no discernible impact on GDP. According to the impulse response function (IRF) study, a GDP shock first has a negative effect on development spending before having a positive reaction. Although GDP might not be a strong indicator of DE in the near run, it becomes increasingly apparent over longer time frames, emphasizing the intricate relationship between macroeconomic factors and fiscal policy.

Artificial Neural Network Regression Modelling of Poverty Index in Nigeria

2024-10-15T15:28:03+08:00

Due to the benefits of Artificial Neural Network (ANN) regression modelling over classical linear regression estimator with respect to faulty tolerance and generalization ability, the study adopted (ANN) regression modelling in order to investigate the impacts of economic variables indices on the poverty index of Nigeria in the years 2018/2019, artificial neural network regression modelling was adopted. This study examined poverty modelling in the realm of (ANN) regression and showcased the contribution of the weight of each predictor variable towards the nodes that determine the Multidimensional Poverty Index (MPI). Most literatures do not interpret the weights and bias of ANN regression, they only described the architecture of the procedures to obtain it. This is the gap this study filled. The study observed that Food insecurity has the highest relative importance with 0.085 magnitude to (MPI) while sanitation has lowest relative importance with magnitude of 0.045 to (MPI).

Developing a New Feature for Vulnerability Risk Scoring Model for Enhanced Cybersecurity

2024-11-17T12:41:59+08:00

As organisations increasingly rely on technology, the risk of cyber threats to data integrity and security grows significantly. Traditional vulnerability risk-scoring models may not adequately address the rapidly evolving nature of cyber threats, necessitating the development of more adaptable and context-specific models. This research aims to achieve two primary objectives: developing a flexible risk-scoring model that can be customised for different industries, companies, or situations, and creating a new feature that accurately reflects the risk score based on the current dataset. The study employs correlation analysis and machine learning-based regression modelling, utilising appropriate evaluation metrics to assess model performance. Results indicate that the K-Nearest Neighbors regression model performs particularly well, offering precise risk assessments. The risk score produced by the model serves as a critical tool for prioritising cybersecurity efforts, where higher scores denote a greater need for immediate action. This research contributes to the field by providing a scalable and customisable framework for developing specialised risk-scoring models, enhancing the effectiveness of cybersecurity strategies across diverse contexts.