R統計回歸模式於環境流行病學之應用

1. Course Objectives: After taking the course, students will be able to 1. Use R program for statistical analysis and apply frequently used statistical models on their own research, 2. Learn how to model continuous exposures and outcomes in an advanced fashion (e.g. splines, polynomial regression), 3. Deal with data when the underlying statistical assumptions do no hold, 4. Apply state-of-art models in epidemiological studies.

2. Course Format For each session, a 2-hour lecture will be delivered followed by a 1-hour hands-on analysis using R statistical program. Students will be able to implement their own codes for statistical analysis taught in the class. 4. Homework Two homework assignments will be distributed throughout the course. Each assignment is based on the material covered in the previous topics. Students are strongly recommended to work in group but must hang-in their own answers along with R codes. 5. Final Project Students will work in groups to frame their major scientific questions based on the environmental dataset distributed at the beginning of the semester. Each group will propose their own scientific objectives by the 1st Progress Report. Preliminary results will be shown at the 2nd Progress Report. At the last week of the semester, each group will present their project in the class, and hang-in their final report within one week. The grade of final project will be based peer’s and instructor’s evaluation. 6. Technical Discussion (2 times) Each group will have two face-to-face discussion sessions with the instructor regarding data management, coding issue, analysis plan, and result throughout the semester. All details of statistical analysis will be discussed in a group-based fashion.

3. Grading Criteria: 60% Final project (a real-world dataset will be distributed for analysis) 20% Two homework assignments (10% for each) 20% Class Participation

Course Text Books:  Peter Dalgaard. Introductory Statistics with R (Paperback) 1st Edition. Springer-Verlag New York, Inc. ISBN 0-387-95475-9 (download link)  P. M. McCullagh and John A. Nelder. Generalized Linear Models. 2nd Edition. Chapman and Hall, London. ISBN 978-0412317606. (download link)  T. J. Hastie and R. J. Tibshirani. Generalize Additive Models. Chapman and Hall, London. ISBN: 0-412-34390-8  David Rupert, M. P. Wand, and R. J. Carroll. Semiparametric Regression. Cambridge University Press. ISBN 978-0521785167  W. N. Venables and B. D. Ripley. 2002 Modern Applied Statistics with S. 4th Edition. Springer. ISBN 0-387-95457-0 Other Useful Reference:  An Introduction to R. Online manual at R website at http://cran.r-project.org/manuals.html  Andreas Krause, Lelvin Olson. 2005. The Basics of S-PLUS. 4th Edition. Springer-Berlag, New York. ISBN 0-387-26109-5  Jose Pinheiro and Douglas Bate. 2000. Mixed-effects models in S and S-PLUS. Springer-Verlag, Berlin. ISBN 0-387-98957-9 Online Course (optional):  Principles of Machine Learning: R Edition (edX DAT276x)  Introduction to Machine Learning  High Level Data Science Process  Overview of Machine Learning  Cleaning and Prepare Data  Data Preparation and Cleaning  Feature Engineering  Getting Started with Supervised Learning  Regression  Classification  Machine Learning Algorithms  Unsupervised Learning  https://courses.edx.org/courses/course-v1:Microsoft+DAT276x+1T2020/course/

地點

Room 307, Medical Building II

時間

by appointment

聯絡方式

email: wenchipan@nycu.edu.tw