[Introduction of New Faculty Member] SAGAWA, Rinka, Research Associate [Joshu/助手]

Self-Introduction

Hello, my name is Rinka Sagawa. I joined the School of International Liberal Studies (SILS) as a Research Associate in April 2026. My research field is Mathematical Statistics, with a particular focus on time series analysis. The practical data exhibits uncertainty with evolution over time. In my previous research, I have focused on periodicity as a key feature of time series data and developed model selection methods for identifying periodic structures in complex datasets. Through my work, I have come to recognize that comprehending a unified statistical framework connecting different academic disciplines plays a central role in making a solution to both the complexity and uncertainty inherent in modern data, as well as in understanding such phenomena on a practical level. I have also found it particularly rewarding to apply statistical methods to real-world data and uncover the underlying structures of observed phenomena from a data-driven perspective. Motivated by these experiences, I continue to pursue research aimed at revealing the structure of complex phenomena through mathematical approaches. At SILS, I am committed to supporting education and research activities while contributing to learning environments where statistical thinking is closely connected to real data and its applications.

Recent Research Interest

My current research focuses on functional time series, a type of time series data, with an interest in developing statistical methods to capture the underlying structures within such data. In recent years, the impact of climate change has increased the importance of accurately understanding meteorological and environmental data. Although such data are observed discreetly, the underlying phenomena evolve continuously over time. By treating these data as functions, we can better capture their essential characteristics. Beyond forecasting, understanding differences in data shapes and patterns of change also plays an important role in interpreting phenomena and supporting decision-making. However, real-world data often include variability, noise, and temporal dependence, making it challenging to properly evaluate their underlying structure. To address these challenges, my research aims to develop statistical methods that can more effectively capture the structure of functional time series while accounting for the realistic properties of observed data. Taking on such challenges, I aim to reveal the mechanisms underlying observed phenomena and contribute to data-driven understanding and decision-making.

Profile

2024〜　Graduate School of Fundamental Science and Engineering, Waseda University 2026〜　Research Associate, School of International Liberal Studies, Waseda University (from April 2026) Research Fields: Mathematical Statistics, Time Series Analysis