A Comparative Analysis of Regression Models for Global Health Prediction

Kalve, Leana (2023) A Comparative Analysis of Regression Models for Global Health Prediction. Bachelor's Thesis, Mathematics.

Preview	Text bMATH_2023_KalveL.pdf.pdf Download (550kB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (130kB)

Abstract

With the increasing availability and accessibility of data, it has become crucial to be able to appropriately interpret and analyze it. In this paper, we aimed to address this need by creating and comparing different regression models on a benchmark life expectancy data set. The models considered for comparison were linear regression, stepwise regression, and mixed effects models. To assess their performance and select the most suitable model, we evaluated them using criteria such as AIC, BIC, and cross-validation. Upon analyzing the results, we found that the regression models and mixed effects models exhibited similar performance in terms of explanatory power, goodness of fit, and prediction accuracy. However, based on careful consideration and several important factors, we advocate for the preference of the mixed effects model for this benchmark data set as it is able to handle nested or hierarchical data structures better.

Item Type:	Thesis (Bachelor's Thesis)
Supervisor name:	Grzegorczyk, M.A. and Krijnen, W.P.
Degree programme:	Mathematics
Thesis type:	Bachelor's Thesis
Language:	English
Date Deposited:	12 Jul 2023 11:15
Last Modified:	12 Jul 2023 11:15
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/30573

Actions (login required)

View Item