Modern multivariable statistical analysis based on the concept of generalized linear models which includes linear, logistic, and Poisson regression, survival analysis, fixed-effects analysis of variance and repeated measures analysis of variance. This course emphasizes the underlying similarity of these methods, the choice of the right method for specific problems, common aspects of model construction, the testing of model assumptions through influence and residual analyses, and the use of graphical and other methods to present results that are readily understood by health researchers. This is a second course in biostatistics, covering multi-predictor methods, including exploratory data analysis and multiple regressions (linear and logistic). This course will cover more details on categorical data (logistic and log linear modeling) and survival analysis (time to event issues). In addition, the new topics will be introduced: fixed effect analysis of variance (anova), mixed effect of analysis of variance, marginal effects, structural equation modelling and causal inferences. Emphasis is on the practical and proper use of statistical methodology and its interpretation. The statistics package STATA will be used throughout the course. Student interests on analyzing a big data set (i.e. IDHS or SUSENAS) they are suggested to take course.
The goal of this course is providing knowledge and skill of the students for analyzing of data using a multivariable technique. At the end of the course, students will be able to:
Passed Introduction Biostatistics I: Basic for Public Health (KUI-6611) and evidence of knowledge of the use of STATA are required. Exceptions to these prerequisites may be made with the consent of the course coordinator if space permitting.
This course is open to a limited number of individuals outside of the MPH's programs. Preference is given to UGM affiliated students, including doctorate students. We regret that auditing is not permitted. To apply for this course please fill out and submit the application available at the study program. Cost and submission information are in the application form.
Lecture will cover statistical theories and its application for health research. It will be given at least twice a week. Each session is about 100 minutes. There will be 14 sessions of lectures during this class (see following Table Class Calendar: 2020-2021).
Students will be given opportunity to explore further details of the lecture materials in the form of discussion and exercise in the class. The teaching assistant and computer programmer are assigned to lead this class discussion and exercise. Their tasks provide student’s better understanding on the lecture materials and problem sets for the previous homework.
Problem sets require the use of STATA (or a comparable statistics package, such as R). You will need to submit STATA code (or code from an equivalent package. If you are using STATA, the code is automatically generated for you as a logfile. You need to cut and paste the relevant code from this automatically generated code into your homework (which will take some understanding of the code itself).
6 Graded Problem Sets………… 60% (late policy: 10% deduction per day late)
In-Class Final Examination...…….. 40%
(All assignment and exam should be submitted in electronics form to avoid plagiarism. Student who conducts plagiarism will not be given grade and she/he has to retake similar class next year).
Chapters to read for this course will be available in printed matter in the class.