Statistics for Climate Research
SAMSI Course: Fall 2017
Outline of Course
This course is being offered in conjunction with the SAMSI year-long research program on Mathematical and Statistical Methods for Climate and the Earth System. The course will cover statistical and computational methods for the analysis of data arising in climate research. Specific topics will include:
·Time series methods and assessments of trends in climatological data
·Analysis of large spatial datasets in climate research
·Methods based on Empirical Orthogonal Functions
·Climate Informatics: the application of machine learning methods and high-performance computing in climate research
·Statistics for climate extremes
·Climate and Health
The course will meet once a week at SAMSI, 4:30 – 7:00 pm Tuesdays. First class: August 29. No class November 21 (Thanksgiving Week). Last class: November 28. Final presentations: December 5.
The course is intended for graduate students (MS and PhD) in Statistics, Mathematics or other mathematically related disciplines. Students in fields such as Environmental Sciences or Geography are also welcome to attend provided they have had at least one graduate-level Statistics course in Linear Models or Regression Analysis. Additional courses in topics such as time series or spatial statistics will be very helpful but are not required. Apart from the statistical prerequisites, participants are expected to have exposure to at least one computing platform such as Matlab or R.
Each student will be expected to conduct a small project applying the techniques of the course to some relevant dataset developed in consultation with the instructors. Depending on the number of students in the course, students may be grouped into teams of two or three students. Each student or team will present its findings at the final class session on Tuesday, December 5, and should also prepare a short written report of its findings. Final grades will be based primarily on these projects. There will be no regular homeworks or exams.