Data-driven analytical methods have seen significant advancements, leading to the proposal of various frameworks for assessing the spatiotemporal impacts of freeway traffic accidents. Typically, the impact of such accidents is identified by comparing traffic speeds under normal conditions with those observed during the accident. This paper introduces a novel framework designed to estimate these impacts. To overcome challenges related to insufficient historical data or concerns about data quality, the framework utilizes predictive speed values to estimate normal expected speeds, rather than relying solely on average values, for calculating the speed change ratio. Furthermore, the framework incorporates an analysis of spatiotemporal mutation points in the speed change ratio, simplifying the impact area by delineating the envelope of the traffic accident propagation curve. This curve reflects trends in speed changes and impact propagation. Additionally, a method for analyzing the error in the spatiotemporal impact range is proposed, allowing for the determination of the maximum and minimum extents of the accident's impact propagation area. The practicality and effectiveness of the proposed framework are demonstrated through a case study.