LEVERAGING PERPLEXITY AI FOR ENHANCED CONCEPTUAL MASTERY AND PRACTICAL APPLICATION IN STATISTICS EDUCATION

Abstract
This research examines the efficacy of Perplexity AI, an advanced search-augmented language model, in revolutionizing statistics education by facilitating deeper comprehension of probabilistic concepts and hands-on data handling. Unlike traditional tools, Perplexity provides instantaneous, citation-backed explanations and step-by-step guidance on topics ranging from probability distributions and hypothesis testing to regression modeling and simulation techniques, enabling students to verify information against reliable sources in real time. Through interactive queries, learners engage in exploratory dialogues that clarify complex statistical queries, generate code snippets for analysis in tools like R or Python, and produce annotated visualizations with contextual interpretations, thereby bridging theoretical knowledge with practical implementation. Perplexity's adaptive response generation accommodates diverse learning paces, encourages source-critical evaluation to combat misinformation, and supports collaborative problem-solving by summarizing peer-reviewed literature on demand. Utilizing a quasi-experimental design with pre- and post-test assessments, surveys on confidence levels, and qualitative interviews, this study measures improvements in statistical accuracy, retention rates, and motivational factors among undergraduate students. The outcomes underscore Perplexity's potential as a scalable, accessible tutor that democratizes statistics learning, offering actionable strategies for instructors to integrate AI-driven search tools into curricula for promoting analytical rigor and lifelong scholarly habits. Keywords - Perplexity AI, statistics education, search-augmented learning, probabilistic reasoning, data modeling, source verification, interactive tutoring, educational technology, student retention, analytical skills.