Environmental Statistics
Staff
Research Topics
Statistical data science provides the most effective means of presenting objective perspectives with scientific evidences. For example, to solve environmental and health issues, it is important to have rational discussions, showing scientific evidences, and without influence by personal feelings. We wish to contribute to solving issues in environmental and life science through research on statistical data science, with a focus on developing computer capabilities.
Statistical modeling and computation for analyzing data in environmental and life science
|
We develop statistical models to analyze complex phenomena that occur in environmental and life science, such as penalized spline regression models, mixed effect models, and Markov random fields, and develop methods for selecting optimal models. |
 Estimated relative risk of German oral cavity cancer with INLA method (Rue et al., 2009) |
Publication List
- Sakamoto, W. (2019). Inference on variance components near boundary in linear mixed effect models. Wiley Interdisciplinary Reviews: Computational Statistics 11(6)
- Sakamoto, W. (2019). Bias‐reduced marginal Akaike information criteria based on a Monte Carlo method for linear mixed‐effects models. Scandinavian Journal of Statistics 46(1) 87 - 115.
- Sakamoto, W. (2016). Cluster detection of disease mapping data based on latent Gaussian Markov random field models. Proceedings of COMPSTAT 2016: 22th International Conference on Computational Statistics, pp. 267-277 (2016.8, Oviedo, Spain)
- Yamaguchi, Y., Sakamoto, W., Goto, M., Staessen, J. A., Wang, J., Gueyffier, F. and Riley, R. D. (2014). Meta-analysis of a continuous outcome combining individual patient data and aggregate data: a method based on simulated individual patient data. Research Synthesis Methods, 5(4), 322-51, doi: 10.1002/jrsm.1119.