In-depth studies of behavioral factors in road accidents using conventional methods are often inconclusive and costly. In a series of studies exploring alternative approaches, 200 cross-flow junction road accidents were sampled from the files of Nottinghamshire Constabulary, England, coded for computer analysis using a specially devised 'Traffic Related Action Analysis Language', and then examined using different computational and statistical techniques. For comparison, the same analyses were also carried out on 100 descriptions of safe turns, and 100 descriptions of hypothetical accidents provided by experienced drivers. The present study used statistical methods to explore the database of cases. The youngest and oldest groups of drivers were found to be over-represented in the junction accidents, and were the least likely to stop before turning. The young drivers had particular problems turning onto major roads. Women were more likely than men to stop before turning; they tended to have their collisions with other women; and they were under-represented as drivers of the non-turning vehicle. In hypothetical accidents, informants tended to blame the younger driver, increasingly so for male informants as they got older. Female informants tended to blame male drivers.