Road safety research is a data-rich field with large social impacts. Like in medical research, the ambition is to build knowledge around risk factors that can save lives. Unlike medical research, road safety research generates empirical findings from messy observational datasets. Records of road crashes contain numerous intersecting categorical variables, dominating patterns that are complicated by confounding and, when conditioning on data to make inferences net of this, observed effects that are subject to uncertainty due to diminishing sample sizes. We demonstrate how visual data analysis approaches can inject rigour into exploratory analysis of such datasets. A framework is presented whereby graphics are used to expose, model and evaluate spatial patterns in observational data, as well as protect against false discovery. The framework is supported through an applied data analysis of national crash patterns recorded in STATS19, the main source of road crash information in Great Britain. Our framework moves beyond typical depictions of exploratory data analysis and helps navigate complex data analysis decision spaces characteristic of modern geographical analysis settings, generating data-driven outputs that support policy interventions and public debate.

Fundamental to the effective use of visualization as an analytic and descriptive tool is the assurance that presenting data visually provides the capability of making inferences from what we see. This paper explores two related approaches to quantifying the confidence we may have in making visual inferences from mapped geospatial data. We adapt Wickham et al.’s `Visual Line-up’ method as a direct analogy with Null Hypothesis Significance Testing (NHST) and propose a new approach for generating more credible spatial null hypotheses. Rather than using as a spatial null hypothesis the unrealistic assumption of complete spatial randomness, we propose spatially autocorrelated simulations as alternative nulls. We conduct a set of crowdsourced experiments (n = 361) to determine the just noticeable difference (JND) between pairs of choropleth maps of geographic units controlling for spatial autocorrelation (Moran’s I statistic) and geometric configuration (variance in spatial unit area). Results indicate that people’s abilities to perceive differences in spatial autocorrelation vary with baseline autocorrelation structure and the geometric configuration of geographic units. These results allow us, for the first time, to construct a visual equivalent of statistical power for geospatial data. Our JND results add to those provided in recent years by Klippel et al. (2011), Harrison et al. (2014) and Kay & Heer (2015) for correlation visualization. Importantly, they provide an empirical basis for an improved construction of visual line-ups for maps and the development of theory to inform geospatial tests of graphical inference.