Institute of Statistical Science, Academia Sinica Campuses

The Institute of Statistical Science at Academia Sinica offers a comprehensive range of advanced courses focused on statistical methodologies, data analysis, and computational statistics. These programs are designed for graduate students, researchers, and professionals seeking to deepen their expertise in statistical sciences.

• Probability Theory: This foundational course covers advanced topics in probability, including measure-theoretic probability, martingales, and stochastic processes. Students explore applications in finance, biology, and engineering, learning to model uncertainty and randomness in complex systems.
• Statistical Inference: Delving into estimation theory, hypothesis testing, and Bayesian methods, this course equips learners with tools for drawing reliable conclusions from data. Emphasis is placed on asymptotic theory, robustness, and modern computational techniques like Markov Chain Monte Carlo (MCMC).
• Multivariate Analysis: Participants study multivariate statistical methods, including principal component analysis (PCA), factor analysis, and canonical correlation. The curriculum addresses high-dimensional data challenges prevalent in genomics and machine learning.
• Time Series Analysis: This course examines forecasting models such as ARIMA, GARCH, and state-space models. Practical sessions involve analyzing economic data, climate trends, and financial time series using R and Python.
• Bayesian Statistics: Advanced Bayesian inference, hierarchical modeling, and prior elicitation are covered. Students apply these to real-world problems in epidemiology and environmental science, incorporating computational tools like Stan and JAGS.
• Machine Learning and Statistics: Bridging statistics and AI, this course explores supervised and unsupervised learning, kernel methods, and deep learning from a statistical perspective. Topics include model selection, overfitting, and causal inference.
• Computational Statistics: Focused on simulation methods, numerical optimization, and big data handling, learners master algorithms for statistical computing, including bootstrap resampling and parallel processing.
• Biostatistics: Tailored for biomedical applications, this covers survival analysis, clinical trial design, and longitudinal data methods. Case studies from public health and drug development highlight ethical considerations in statistical practice.
• Spatial Statistics: Addressing geospatial data, the course introduces geostatistics, point processes, and spatial regression. Applications include environmental monitoring and urban planning.
• Experimental Design: Principles of designing efficient experiments, including factorial designs, response surface methodology, and optimal designs, are taught with software implementation.

These courses emphasize theoretical rigor alongside practical skills, often involving interdisciplinary collaborations. The institute's programs foster research innovation, preparing students for careers in academia, industry, and government. Seminars and workshops supplement the curriculum, featuring guest lectures from global experts. With state-of-the-art computing facilities, the campus supports hands-on projects in data-intensive fields. Overall, the educational offerings at the Nangang Campus promote a deep understanding of statistical science's role in solving contemporary challenges, from AI ethics to climate modeling. Graduates emerge as proficient statisticians capable of advancing knowledge across disciplines.