Bayesian semi-parametric spatial modelling of intimate partner violence in Namibia using 2013 Demographic Health Survey Data

Abstract

Background Intimate partner violence (IPV) is an important public health problem with health and socioeconomic consequences and is endemic in Namibia. Studies assessing risk factors for IPV often use logistic and Poisson regression without geographical location information and spatial effects. We used a Bayesian spatial semi-parametric regression model to determine the risk factors for IPV in Namibia; assess the non-linear effects of age difference between partners and determine spatial effects in the different regions on IPV prevalence. Methods We used the couples’ dataset of the 2013–2014 Namibia Demographic and Health Survey (DHS) obtained on request from Measure DHS. The DHS domestic violence module included 2226 women. We generated a binary variable measuring IPV from the questions “ever experienced physical, sexual or emotional violence?” Covariates included respondent’s educational level, age, couples’ age difference, place of residence and partner’s educational level. All estimation was done with the full Bayesian approach using R version 3.5.2 implementing the R2BayesX package. Results IPV country prevalence was 33.3% (95% CI = 30.1–36.5%); Kavango had the highest [50.6% (95% CI = 41.2–60.1%)] and Oshana the lowest [11.5% (95% CI = 3.2–19.9%)] regional prevalence. IPV prevalence was highest among teenagers [60.8% (95% CI = 36.9–84.7%)]). The spatial semi-parametric model used for adjusted results controlled for regional spatial effects, respondent’s age, age difference, respondent’s years of education, residence, wealth, and education levels. Women with higher education were 50% less likely to experience IPV [aOR: 0.46, 95% CI = 0.23–0.87]. For non-linear effects, the risk of IPV was high for women ≥ 5 years older or ≥ 25 years younger than their partners. Younger and older women had higher risks of IPV than those between 25 and 45 years. For spatial variation of IPV prevalence, northern regions had low spatial effects while western regions had very high spatial effects. Conclusion The prevalence of IPV among Namibia women was high especially among teenagers, with higher educational levels being protective. The risk of IPV was lower in rural than urban areas and higher with wide partner age differences. Interventions and policies for IPV prevention in Namibia are needed for couples with wide age differences as well as for younger women, women with lower educational attainment and in urban and western regions.

Factors Associated With Domestic Violence Against Women at Different Stages of Life: Findings From a 19-Year Longitudinal Dataset From the MINIMat Trial in Rural Bangladesh (2001–2020)

“…We found that more than 10 years age difference between the partners was associated with lower odds of experiencing physical DV at the 18-year follow-up. There exist studies that found contrary results compared to our findings and argued that in patriarchal settings (such as Bangladesh), a higher age gap between the partners might reduce women’s negotiating power and result in a higher risk of violence (Ojifinni et al, 2021). This may be true, particularly at the initial period after marriage, but as shown in our study, 18 years after the birth of the index child such spousal age gap provided protection against physical violence.…”

Determinants of Emotional Intimate Partner Violence against Women and Girls with Children in Mexican Households: An Ecological Framework

“…Due to the hierarchical data structure, in which individual observations are connected to the information for the municipalities, and these, in turn to the state information, we introduce random effects. To explore whether IPV follows a particular spatial pattern, as found by Ojifinni et al (2021) , we also include the municipal centroid coordinates.…”

Bayesian spatial modelling of intimate partner violence and associated factors among adult women and men: evidence from 2019/2020 Rwanda Demographic and Health Survey

“…Intimate partner violence (IPV) refers to all forms of behaviour within an intimate relationship that causes physical, sexual or psychological harm, including acts of physical aggression, sexual coercion, psychological abuse, and controlling behaviours [ 1 , 2 ]. It has been recognized globally as an important public health problem and a huge violation of human rights [ 3 ] which has been associated with significant morbidity and mortality as well as health and socioeconomic effects among both women and men [ 4 , 5 ].…”

“…There has been growing interest in spatial analysis techniques in recent years as a tool for an in-depth understanding of public health problems including identifying IPV hotspots, spatial distribution, patterns and effects. Intimate partner violence has been shown in some studies to be spatially distributed [ 1 , 27 , 28 ], however none of the studies have used flexible structured additive regression models to estimate district spatial effects while adjusting for other covariates in studying IPV against men and women. A recent study [ 13 ] using the 2019/2020 Rwandan Demographic and Health Survey (RDHS) dataset looked at the factors associated with IPV against women and men but did not consider spatial heterogeneity of IPV.…”