Measuring sexual violence stigma in humanitarian contexts: assessment of scale psychometric properties and validity with female sexual violence survivors from Somalia and Syria

Abstract

Background: Valid measures of sexual violence stigma that can be readily incorporated into program monitoring and evaluation systems are needed to strengthen gender-based violence (GBV) services in humanitarian emergencies. This study sought to assess the psychometric properties, construct validity, and measurement invariance of sexual violence stigma scales among female Somali GBV survivors in Kenya and Syrian GBV survivors in Jordan to identify an abbreviated scale that could be used across humanitarian contexts.

Methods: We administered measures of sexual violence stigma to 209 female survivors of sexual violence aged 15 and older in Kenya and Jordan. Exploratory factor analysis was used to assess the underlying latent structure, and Item Response Theory was used to estimate item difficulty and discrimination parameters to guide efforts to shorten the scales. Differential item functioning (DIF) by site was assessed using Multiple Indicators, Multiple Causes models. Construct validity of the sexual violence stigma scales was assessed by estimating correlations with functional impairment, depression, and disability.

Results: The sexual violence stigma measure exhibited distinct factor structures among Somali and Syrian GBV survivors. Among Somali survivors, a two-factor model with separate felt (10 items) and enacted (4 items) stigma constructs was identified, with scales for both domains exhibiting good internal consistency (Cronbach's alpha = 0.93 and 0.88, respectively). In Jordan, a single factor solution was uncovered for a 15-item stigma scale with good internal consistency (alpha = 0.86). The shortened core sexual stigma scale consisting of the 4 items that did not exhibit DIF had a Cronbach's alpha of 0.82 in Kenya and 0.81 in Jordan. The felt stigma scale in Kenya, the full stigma scale in Jordan, and abbreviated core stigma scales in both countries were meaningfully correlated with depression, while correlations with functional impairment were weaker and inconsistent across scales.

Conclusions: An abbreviated core set of invariant perceived and internalized sexual violence stigma items demonstrated evidence of construct validity in two diverse settings. The ability of this measure to be efficiently administered as a part of routine program monitoring and evaluation activities, with the potential addition of items from a measurement bank to improve contextual relevance, can facilitate improvements in the delivery and quality of gender-based violence programs in humanitarian emergencies.

Keywords: Item response theory; Measurement; Psychometrics; Sexual violence; Somalia; Stigma; Syria.

Fig. 1

Average stigma item score by country