Distributed data analytics in edge computing has become a prominent research area, focusing on performing computation-intensive analytics close to data sources to reduce latency, bandwidth usage, and cloud dependency. Research papers in this domain explore frameworks and architectures that enable real-time and near-real-time processing of massive, heterogeneous data generated by IoT devices, autonomous vehicles, smart healthcare systems, industrial automation, and smart cities. Studies highlight techniques such as in-network processing, hierarchical edge–fog–cloud analytics, and collaborative learning to efficiently aggregate and analyze distributed data. Recent works leverage machine learning, deep learning, and federated learning for predictive analytics, anomaly detection, and decision-making at the edge, while addressing challenges like data heterogeneity, dynamic workloads, and resource constraints. Security- and privacy-aware distributed analytics frameworks are also a key focus, using encryption, differential privacy, and blockchain mechanisms to safeguard sensitive information. Additionally, research investigates fault-tolerant, resilient, and adaptive data analytics strategies to maintain service continuity under network variability and node failures. Overall, distributed data analytics in edge computing enables scalable, low-latency, and intelligent processing, bridging the gap between data generation and actionable insights in next-generation cyber-physical systems.