Treffer: From Clicks to Conversations: Evaluating the Effectiveness of Conversational Agents in Statistical Analysis.

AbstractThe rapid evolution of data science forced individuals with different backgrounds to adapt to statistical analysis. We hypothesize that conversational agents are better suited for statistical analysis than traditional graphical user interfaces (GUI). In this work, we propose a novel conversational agent, <italic>StatZ</italic>, for statistical analysis. We evaluate <italic>StatZ</italic> relative to statistical software—SPSS, SAS, Stata, and JMP—in terms of accuracy, task completion time, user experience, and user satisfaction. We experimented with 51 participants from diverse backgrounds with proposed analysis question.Our design assessed each participant’s ability to perform statistical tasks using GUI-based tools and our conversational agent. Results indicate that conversational agents significantly outperform GUI statistical software in all assessed metrics, including quantitative (task completion time, accuracy, and user experience), and qualitative (user satisfaction). Our findings underscore the potential of conversational agents to enhance statistical analysis, reducing cognitive load and learning curves enabling data analysis capabilities. [ABSTRACT FROM AUTHOR]