Statistical Data Types and Visualisation Techniques in Clinical and Public Health Research: A Methodological Framework and Practical Guide

Abstract Rapid expansion of clinical and public health data has made statistical analysis an integral part of medical research, disease surveillance and health policy. While much guidance exists on the choice of statistical methods, relatively less attention has been paid to how statistical findings are visually communicated. In practice, graphical displays are often poorly matched with the type of data, their distribution or the purpose of analysis. Such mismatches can lead to misinterpretation, even when statistical analyses have been conducted appropriately. This is especially problematic in clinical and public health settings, where visual summaries frequently underpin rapid interpretation and decision-making by diverse audiences. In this article, we present a structured methodological approach that connects common statistical data types used in clinical and public health research with their analytical objectives and appropriate visualisation methods. We rely on established principles from biostatistics, epidemiology and information visualisation and frame visualisation as an intrinsic component of statistical reasoning rather than a purely presentational step. The framework covers categorical, continuous, longitudinal, multivariate, model-based and spatial data and identifies common forms of visual misuse together with their methodological consequences. By matching data structure, analytical intent and visualisation form, this framework provides practical guidance to support clearer interpretation and communication of quantitative findings. It is intended for researchers, clinicians, public health practitioners, data analysts and educators engaged in the analysis or presentation of health data. Future studies should examine how framework-informed visualisation influences interpretation and decision-making in real-world clinical and public health settings.