Ecological Fallacies and the Analysis of Areal Census Data

Abstract

The author examines problems related to the fact that in many countries, census data are only reported for areal units and not at the individual level. Attention is paid to the question of ecological fallacy problems that arise from this situation. Data from a 10 percent sample of the United Kingdom population and individual census data from Italy are used to illustrate the problem. "It is concluded that ecological fallacy effects are endemic to areal census data, although their magnitude is perhaps not as large as might have been expected. The principal difficulty is that there is at present no way of predicting in advance the degree of severity likely to be associated with particular variables and particular techniques. Finally, a suggestion is made concerning how the potentially serious practical consequences can be reduced."

Distribuição espacial da leptospirose no Rio Grande do Sul, Brasil: recuperando a ecologia dos estudos ecológicos

“…Os diferentes resultados obtidos segundo os recortes espaciais foi chamado de problema da unidade de área modificável (Openshaw, 1984). A maior parte destes trabalhos mostra que as correlações aumentam à medida que se agregam os dados em unidades espaciais maiores.…”

“…Outras formas de estratificação e visualização de indicadores em mapas devem ser buscadas. Segundo Openshaw (1984), uma das formas de controlar a influên-cia de fatores de confusão nos estudos ecológi-cos pode ser a escolha correta de unidades de agregação de dados.…”

Relationships of Land Use Mix with Walking for Transport: Do Land Uses and Geographical Scale Matter?

“…Measurement of data at a single geographical scale can avoid the introduction of errors associated with aggregating data collected at different geographical scales. 35 Thus, examination of the impact of heterogeneity in administrative boundary size, and how to correct for it, is needed.…”

Regionalisierung von Gesundheitsindikatoren

“…In den USA werden die Verfahren in der Regel auf der Ebene der sogenannten counties angewendet, die durchschnittlich eine kleinere Bevölkerung aber eine größere Fläche als Kreise und kreisfreien Städte in Deutschland haben. Generell ist bei der Interpretation von Aggregatdaten zu beachten, dass sich die Wahl der Ebene der Regionalisierung von aggregierten Daten auf die Ergebnisse der Analysen auswirkt (sogenanntes Modifiable-Area-Unit-Problem (MAUP) [32]). …”