http://journals.editononline.com/index.php/jmds/issue/feedJournal of Mathematics and Data Science (JMDS)2024-11-05T10:30:04+00:00Editon Consortium Publishingeditor@editononline.comOpen Journal Systems<p><a href="https://journals.editononline.com/index.php/jmds"> <strong>Journal of Mathematics and Data Science (ISSN: 3005-544X)</strong></a> is a double-blind peer reviewed, open access, online Journal published by “<a href="https://editononline.com/"><strong>Editon Consortium Publishin</strong>g</a>”, East Africa, Kenya. The Journal publishes original scholarly research (empirical and theoretical), in form of case studies, reviews and analyses in mathematics, actuarial sciences, data science and related areas.</p>http://journals.editononline.com/index.php/jmds/article/view/645Analysing the impact of age, wealth, mother's education, area of residence, and gender on child weight: a regression approach2024-11-05T10:30:04+00:00Grace Chumbagchepkorir@kabarak.ac.kePerpetual Petronillah Mumbua Munyaopmumbua@kabarak.ac.ke<p><strong>Abstract</strong></p> <p>The purpose of this article is to analyse the impact of age, wealth, mother's education, area of residence, and gender all together on child weight using multiple linear regression model. Previous studies have examined the effects of these factors on child weight singly or in pairs but not all together. The various factors affecting child weight that contribute to the broader issues of malnutrition and obesity need to be examined. This study addresses this issue with the aim of identifying the most significant predictors of healthy child weight. The data were collected from a secondary source for a sample size of 760 children aged 0-59 months. The data were analysed using multiple linear regression with SPSS software. The correlation coefficient (0.861) between the observed and predicted values of the dependent variable (child weight) suggests a strong positive correlation. 74.2 per cent of the variability in child weight is explained by the predictors in this model, indicating a good fit. The model also explains 74per cent of the variance, suggesting a robust fit. Age, gender, wealth, and mother's education are significant predictors of child weight, whilst area of residence is not statistically significant, though location-specific strategies may still be beneficial for child health outcomes. Based on the findings of this study, public health programs should prioritise age-appropriate nutrition, gender-sensitive interventions, and enhanced maternal education to improve child weight outcomes.</p>2024-11-25T00:00:00+00:00Copyright (c) 2024 Journal of Mathematics and Data Science (JMDS)