Asian Journal of Probability and Statistics

This study develops a rank-based analytical framework for characterising the cancer burden in Ghana using GLOBOCAN 2022 estimates. The analysis examines structural relationships among incidence, mortality, cumulative risk, and age-standardised rates across major cancer types and introduces a normalised severity index for comparing relative lethality patterns. Linear, log-log, power-law, and exponential models were fitted to evaluate incidence-mortality scaling and rank-dependent decay. Model performance was assessed using the coefficient of determination, root mean square error, Akaike information criterion, and 95% confidence intervals. The results show a strong positive relationship between incidence and mortality, with evidence of non-linear scaling across cancer sites. Cancer incidence and mortality declined markedly with increasing rank, indicating that a limited number of cancer types accounted for a substantial proportion of the estimated national burden. High mortality-to-incidence ratios were observed for pancreatic, lung, oesophageal, liver, and stomach cancers, whereas breast, prostate, and corpus uteri cancers showed lower relative mortality. The severity-based exponential-saturation model produced close agreement between observed and calculated values, supporting its usefulness as a descriptive comparative measure. However, the findings are derived from modelled national estimates for a single year and should not be interpreted causally. The proposed framework may support structured burden comparison and prioritisation in data-limited settings, but external validation using longitudinal, population-based cancer registry data is required.