The clandestine nature of covert networks makes reliable data difficult to obtain and leads to concerns with missing data. We explore the use of network models to represent missingness mechanisms. Exponential random graph models provide a flexible way of parameterising departures from conventional missingness assumptions and data management practices. We demonstrate the effects of model specification, true network structure, and different not-at-random missingness mechanisms across six empirical covert networks. Our framework for modelling realistic missingness mechanisms investigates potential inferential pitfalls, evaluates decisions in collecting data, and offers the opportunity to incorporate non-random missingness into the estimation of network generating mechanisms.

Family planning is heralded as one of the ten most significant contemporary public health achievements, yet it remains underutilized in countries, especially in Sub-Saharan Africa, that might most benefit from it. While substantial strides have been made to address supply-side barriers to modern contraceptive (MC) adoption in these regions, demand-side obstacles like personal or partner opposition are less understood. This study investigates the role of social influence in shaping MC demand in communities with low modern Contraceptive Prevalence Rates (mCPR). Using the Structured Influence Process (SIP) framework, we examine how an individual's social relations and exposure to persuasive messages, either in support of or opposition to MC use, jointly influence their decision to adopt or reject contraceptives. Using survey data from two different Kenyan communities, both exhibiting low mCPR but one relatively higher than the other, we observe that mere exposure to MC users or non-users during free-time interactions is insufficient to sway usage decisions. However, the combination of direct contact with contraceptive users and persuasive messages emerges as a potent force of influence. In the lower mCPR community, only a few types of persuasive messages are circulated, and they are all consistently influential in either encouraging or discouraging MC use. These messages primarily appeal to individuals’ desire to do what is “right” by emphasizing social validation and deference to trusted authorities, or their desire to do what is “liked” by reinforcing interpersonal bonds and reciprocal obligations. In the higher mCPR community, a broader range of persuasive messages effectively promote MC use; however, only those invoking social shame effectively discourage it. These findings highlight a crucial distinction between “prevalent vs. persuasive” messaging: While many persuasive messages may be prevalent (i.e., used often), only a subset are also persuasive. Recognizing which messages are merely pervasive versus those that are genuinely effective is vital for efficiently allocating resources to promote or counter MC use narratives. Leveraging research across network science and persuasion, this study contributes to a more comprehensive understanding of how social influence shapes contraceptive decision-making.

Network-based analyses have effectively understood customer preferences through interactions between customers and products, particularly for tailored product design. However, research applying this analysis to diverse customers with varied preferences is limited. This paper introduces a market-segmented network modeling approach, guided by customer preference, to explore heterogeneity in customers’ two-stage decision-making process: consideration-then-choice. In heterogeneous markets, customers with similar characteristics or purchasing similar products can exhibit different decision-making processes. Therefore, this method segments customers based on preferences rather than just characteristics, allowing for more accurate choice modeling. Using joint correspondence analysis, we identify associations between customer attributes and preferred products, characterizing market segments through clustering. We then build individual bipartite customer–product networks and apply the exponential random graph model to compare the product features influencing customer considerations and choices in various market segments. Using a US household vacuum cleaner survey, our method detected different customer preferences for the same product attribute at different decision-making stages. The market-segmentation model outperforms the non-segmented benchmark in prediction, highlighting its accuracy in predicting varied customer behaviors. This study underscores the vital role of preference-guided segmentation in product design, illustrating how understanding customer preferences at different decision stages can inform and refine design strategies, ensuring products align with diverse market needs.

Introduction Longitudinal studies can provide timely and accurate information to evaluate and inform COVID-19 control and mitigation strategies and future pandemic preparedness. The Optimise Study is a multidisciplinary research platform established in the Australian state of Victoria in September 2020 to collect epidemiological, social, psychological and behavioural data from priority populations. It aims to understand changing public attitudes, behaviours and experiences of COVID-19 and inform epidemic modelling and support responsive government policy.

Methods and analysis This protocol paper describes the data collection procedures for the Optimise Study, an ongoing longitudinal cohort of ~1000 Victorian adults and their social networks. Participants are recruited using snowball sampling with a set of seeds and two waves of snowball recruitment. Seeds are purposively selected from priority groups, including recent COVID-19 cases and close contacts and people at heightened risk of infection and/or adverse outcomes of COVID-19 infection and/or public health measures. Participants complete a schedule of monthly quantitative surveys and daily diaries for up to 24 months, plus additional surveys annually for up to 48 months. Cohort participants are recruited for qualitative interviews at key time points to enable in-depth exploration of people’s lived experiences. Separately, community representatives are invited to participate in community engagement groups, which review and interpret research findings to inform policy and practice recommendations.