Correct identification of ethnicity is central to many epidemiologic analyses. Unfortunately, ethnicity data are often missing. Successful classification typically relies on large databases (n > 500,000 names) of known name-ethnicity associations. We propose an alternative naïve Bayesian strategy that uses substrings of full names. Name and ethnicity data for Malays, Indians, and Chinese were provided by a health and demographic surveillance site operating in Malaysia from 2011-2013. The data comprised a training data set (n = 10,104) and a test data set (n = 9,992). Names were spliced into contiguous 3-letter substrings, and these were used as the basis for the Bayesian analysis. Performance was evaluated on both data sets using Cohen's κ and measures of sensitivity and specificity. There was little difference between the classification performance in the training and test data (κ = 0.93 and 0.94, respectively). For the test data, the sensitivity values for the Malay, Indian, and Chinese names were 0.997, 0.855, and 0.932, respectively, and the specificity values were 0.907, 0.998, and 0.997, respectively. A naïve Bayesian strategy for the classification of ethnicity is promising. It performs at least as well as more sophisticated approaches. The possible application to smaller data sets is particularly appealing. Further research examining other substring lengths and other ethnic groups is warranted.
Background Verbal autopsies have gained considerable ground as an acceptable alternative to medically determined cause of death. Unlike with clinical or more administrative settings for data collection, verbal autopsies require significant involvement of families and communities, which introduces important social and cultural considerations. However, there is very little clear guidance about the methodological issues in data collection. The objectives of this case study were: to explore the range of bereavement rituals within the multi-ethnic, multi-faith population of the district; to investigate the preparedness of communities to talk about death; to describe the verbal autopsy process; to assess the effects of collecting verbal autopsy data on data collectors; and to determine the most accurate sources of information about deaths in the community. Methods A case study approach was used, using focus group discussions, indepth interviews and field notes. Thematic analyses were undertaken using NVivo. Results Consideration of cultural bereavement practices is importance to acceptance and response rates to verbal autopsies. They are also important to the timing of verbal autopsy interviews. Well trained data collectors, regardless of health qualifications are able to collect good quality data, but debriefing is important to their health and well being. This article contributes to guidance on the data collection procedures for verbal autopsies within community settings.