Biostatistics
This course focuses on fundamental principles of multivariate statistical analyses in biostatistics, including multiple linear regression, multiple logistic regression, analysis of variance, and basic epidemiology concepts. The fundamental theories are applied to analyze various biomedical applications ranging from laboratory data to large-scale epidemiological data. In particular, this course focuses on multivariate statistical analyses, which involve more than one variable and take into account several variables on the responses of interest. This course focuses on fundamental principles of multivariate statistical analyses in biostatistics, including multiple linear regression, multiple logistic regression, analysis of variance, and basic epidemiology concepts. The fundamental theories are applied to analyze various biomedical applications ranging from laboratory data to large-scale epidemiological data. In particular, this course focuses on multivariate statistical analyses, which involve more than one variable and take into account several variables on the responses of interest. In addition, although statistical learning and machine learning are different, both learning approaches play a key role in inference and prediction. This course compares statistical learning and deep learning in the context of biostatistics.
https://engineering.purdue.edu/online/courses/mulitvariate-analyses-biostatistics
https://engineering.purdue.edu/online/@@site-logo/Purdue-Engr2.jpg
Biostatistics
This course focuses on fundamental principles of multivariate statistical analyses in biostatistics, including multiple linear regression, multiple logistic regression, analysis of variance, and basic epidemiology concepts. The fundamental theories are applied to analyze various biomedical applications ranging from laboratory data to large-scale epidemiological data. In particular, this course focuses on multivariate statistical analyses, which involve more than one variable and take into account several variables on the responses of interest. This course focuses on fundamental principles of multivariate statistical analyses in biostatistics, including multiple linear regression, multiple logistic regression, analysis of variance, and basic epidemiology concepts. The fundamental theories are applied to analyze various biomedical applications ranging from laboratory data to large-scale epidemiological data. In particular, this course focuses on multivariate statistical analyses, which involve more than one variable and take into account several variables on the responses of interest. In addition, although statistical learning and machine learning are different, both learning approaches play a key role in inference and prediction. This course compares statistical learning and deep learning in the context of biostatistics.
BME50100
Credit Hours:
3
Learning Objective:
The course is designed for graduate students to build a foundation of multivariate statistical analyses, to analyze large data with multiple variables, to formulate appropriate models from different perspectives, and to correctly interpret statistical estimates. By the completion of this course, students will be able to:
- Understand fundamental concepts in multivariate regression analyses
- Apply data analyses using an advanced statistical software package
- Formulate research questions into suitable multivariate frameworks
- Analyze appropriate statistical estimates from multivariate analyses.
Statistical learning is all about sample, population, and hypothesis for statistical inference. On the other hand, machine learning is centered in prediction and classification. Some key differences between statistical learning and deep learning can be learned from multivariate regression.
Description:
This course focuses on fundamental principles of multivariate statistical analyses in biostatistics, including multiple linear regression, multiple logistic regression, analysis of variance, and basic epidemiology concepts. The fundamental theories are applied to analyze various biomedical applications ranging from laboratory data to large-scale epidemiological data. In particular, this course focuses on multivariate statistical analyses, which involve more than one variable and take into account several variables on the responses of interest. This course focuses on fundamental principles of multivariate statistical analyses in biostatistics, including multiple linear regression, multiple logistic regression, analysis of variance, and basic epidemiology concepts. The fundamental theories are applied to analyze various biomedical applications ranging from laboratory data to large-scale epidemiological data. In particular, this course focuses on multivariate statistical analyses, which involve more than one variable and take into account several variables on the responses of interest. In addition, although statistical learning and machine learning are different, both learning approaches play a key role in inference and prediction. This course compares statistical learning and deep learning in the context of biostatistics.
F2019 Syllabus
Topics Covered:
Simple linear regression; Correlation analysis; Multiple linear regression; Screening and diagnostic tests; Simple logistic regression; Multiple logistic regression; Analysis of variance; Multiple comparisons; Survival analysis; Introduction of deep learning
Prerequisites:
IE 330 Probability and Statistics in Engineering II or equivalent basic statistics course.
Applied / Theory:
70 / 30
Web Address:
https://mycourses.purdue.edu/
Web Content:
Link to my current website, syllabus, grades, lecture notes, homework assignments, solutions, quizzes, chat room and message board.
Homework:
Students will be evaluated in terms of their performance on weekly assignment. The assignment will be evaluated critically. The assignment will include hands-on analyses of basic principles of concepts covered during lectures using small sample examples.
Projects:
None
Exams:
One take-home midterm. One final take-home final. Each exam will cover different content. Final exam not cumulative. Format of exams subject to change.
Textbooks:
Official textbook information is now listed in the Schedule of Classes. NOTE: Textbook information is subject to be changed at any time at the discretion of the faculty member. If you have questions or concerns please contact the academic department.
Dupont WD. Statistical Modeling for Biomedical Researchers. Cambridge University Press, 2nd edition, 2009. ISBN:9780521614801 http://biostat.mc.vanderbilt.edu/dupontwd/wddtext/index.html
Computer Requirements:
ProEd Minimum Computer Requirements. This course will also conduct basic operations in large-scale statistical analyses with statistical software packages (e.g. STATA). Students will have access to the packages in BME computer lab. Six-month ($38) or one-year ($54) STATA licenses are also available to purchase his/her own student version (http://www.stata.com/order/new/edu/gradplans/student-pricing). Stata/SE is available through Purdue ITaP https://communityhub.purdue.edu/storefront/product/stata_personal STATA is chosen for the breadth and depth of its statistical methods, its ease of use, and its good documentation. However, students can use other software packages such as SAS, SPSS, and R (free statistical software). Overall, minimal help on STATA will be provided, given that this course is intended to teach biostatistics not a package. It should be noted that STATA is a user-friendly easy-to-use statistical software package that is commonly used in clinical and biomedical research.
ProEd Minimum Requirements:
view
