How and when doula support increases confidence in women experiencing socioeconomic adversity: Findings from a realist evaluation of an Australian volunteer doula program

Abstract

How women are cared for while having a baby can have lasting effects on their lives. Women value relational care with continuity-when caregivers get to know them as individuals. Despite evidence of benefit and global policy support, few maternity care systems across the world routinely offer relational continuity. Women experiencing socioeconomic adversity have least access to good quality maternity care. Community-based doula support programs offer complementary care for these women and are known to, on average, have positive outcomes. Less understood is how, when, and why these programs work. A realist evaluation of an Australian volunteer doula program explored these questions. The program provides free social, emotional, and practical support by trained doulas during pregnancy, birth, and early parenting. This paper reports the testing and refinement of one program theory from the larger study. The theory, previously developed from key informant interviews and rapid realist review of literature, hypothesised that support increased a woman's confidence via two possible pathways-by being with her and enabling her to see her own strength and value; and by praising her, and her feeling validated as a mother. This study aimed to test the theory in realist interviews with clients, focus groups with doulas, and with routinely collected pre-post data. Seven English-speaking and six Arabic-speaking clients were interviewed, and two focus groups with a total of eight doulas were conducted, in January-February 2020. Qualitative data were analysed in relation to the hypothesised program theory. Quantitative data were analysed for differential outcomes. Formal theories of Recognition and Relational reflexivity supported explanatory understanding. The refined program theory, Recognition, explains how and when a doula's recognition of a woman, increases confidence, or not. Five context-mechanism-outcome configurations lead to five outcomes that differ by nature and longevity, including absence of felt confidence.

Fig 1. Evaluation design, with scope of this paper highlighted.

Fig 2. Routinely collected pre-post birth confidence data available for analysis (respondent group, n = 103).

Fig 3. Short- and long-term confidence-related outcomes for women.