Measurement of delayed bathing and early initiation of breastfeeding: a cross-sectional survey exploring experiences of data collectors in Ethiopia

Background: Delayed bathing and early initiation of breastfeeding are among the essential interventions recommended to save newborn lives. Although survey coverage reports are key to monitoring these interventions, few studies investigated whether such reports accurately reflect the proportion of mothers and children who received these interventions. In order to gather accurate data, guidance on how to interview and probe mothers is provided. In this study, we investigated experiences of data collectors when asking mothers survey questions that assessed delayed bathing and early initiation of breastfeeding. Methods: In November 2013, using a self-administered semi-structured questionnaire, we interviewed data collectors who had taken part in a population-based newborn health household survey in Ethiopia during October-November 2013. A total of 130 out of 160 invited data collectors completed and returned the self-administered questionnaire. Descriptive statistics were used to analyse quantitative data using SPSS software version 19. Qualitative data showing the variety of probes used by data collectors was analysed by listing, screening to identify common themes, and grouping by category. Results: Most data collectors reported that, in their opinion, mothers were able to understand the meaning of the question about newborn bathing (n = 102, 79%) and breastfeeding initiation (n = 106, 82%) without the need for probes. However, fewer mothers were able to recall the event for either newborn behaviours and describe it in minutes, hours or days without the need for probes. Overall, only 26% (n = 34) and 34 % (n = 44) of all data collectors reported that they did not need any probing for the questions related to newborn bathing and breastfeeding initiation questions, respectively. We identified a variety of probes used by data collectors and present examples. Conclusion: Considerable probing was necessary to facilitate maternal recall of the events and approximate their responses of time regardless of mothers' age, level of education and parity. This could potentially lead to inaccurate coverage reports due to subjective and inconsistent interpretation of the indicators. Therefore, we recommend inclusion of standard probes or follow-on questions to the existing survey tools assessing the two indicators. Data collectors also require further guidance in using appropriate probes to gather accurate maternal responses.