Error propagation models to examine the effects of geocoding quality on spatial analysis of individual-level datasets

Abstract

The quality of geocoding has received substantial attention in recent years. A synthesis of published studies shows that the positional errors of street geocoding are somewhat unique relative to those of other types of spatial data: 1) the magnitude of error varies strongly across urban-rural gradients; 2) the direction of error is not uniform, but strongly associated with the properties of local street segments; 3) the distribution of errors does not follow a normal distribution, but is highly skewed and characterized by a substantial number of very large error values; and 4) the magnitude of error is spatially autocorrelated and is related to properties of the reference data. This makes it difficult to employ analytic approaches or Monte Carlo simulations for error propagation modeling because these rely on generalized statistical characteristics. The current paper describes an alternative empirical approach to error propagation modeling for geocoded data and illustrates its implementation using three different case-studies of geocoded individual-level datasets. The first case-study consists of determining the land cover categories associated with geocoded addresses using a point-in-raster overlay. The second case-study consists of a local hotspot characterization using kernel density analysis of geocoded addresses. The third case-study consists of a spatial data aggregation using enumeration areas of varying spatial resolution. For each case-study a high quality reference scenario based on address points forms the basis for the analysis, which is then compared to the result of various street geocoding techniques. Results show that the unique nature of the positional error of street geocoding introduces substantial noise in the result of spatial analysis, including a substantial amount of bias for some analysis scenarios. This confirms findings from earlier studies, but expands these to a wider range of analytical techniques.

Comparación de las aplicaciones de Google y Yahoo para la geocodificación de direcciones postales con fines epidemiológicos

“…No se ha encontrado direccionalidad en los errores en las dos ciudades, coincidiendo con Zandbergen et al 8 .…”

“…El programa libre GvSig prevé la geocodificación masiva de direcciones para su próxima versión 2 5 . Es conocido que la geocodificación tiene asociado un error o sesgo que puede introducir un ruido significativo en los análisis epidemiológicos espaciotemporales 6-7 y afectar a los resultados 8 . Estos errores pueden deberse: 1)A la mala calidad del fichero de las direcciones (errores tipográficos, símbolos no reconocibles, etc.…”

“…Si bien hay trabajos que han estudiado estos errores con recursos de EEUU [6][7][8] , no se han encontrado trabajos que evalú-en este error en municipios de España.…”

The effect of acquisition error and level of detail on the accuracy of spatial analyses

“…For example, Goulden, Hopkinson, Jamieson, and Sterling (2016) investigate the propagation of positional error in point clouds to the calculation of various topographic attributes, such as slope, aspect, and watershed area. Griffith, Millones, Vincent, Johnson, and Hunt (2007) and Zandbergen, Hart, Lenzer, and Camponovo (2012) observe the influence of positional error in geocoded addresses on various administrative use cases such as the assignment of houses to census blocks, and allocation of students to their nearest public schools. Hartzell, Gadomski, Glennie, Finnegan, and Deems (2015) estimate the propagation of positional error from terrestrial laser scanning to the measurement of snow volume.…”

Using address histories in health research

“…The accuracy of different geocoding schemes has been a frequent topic of research within the last 10 years. Positional error of geocoding schemes varies widely and can be dependent upon type of reference data selected [10]- [13]. Similarly, match rates vary with type of reference data; some reference data require an address to match exactly with reference data while others allow inference to dictate matches [13].…”