Description: This course will introduce the theory and methods of spatial and spatio-temporal statistics. It will present spatial and spatio-temporal statistical models and will discuss methods for inference on spatial processes within a geostatistical and a hierarchical Bayesian framework.
Prerequisites: EPID600, BIOSTAT522 and BIOSTAT523 for epid students; BIOSTAT650, BIOSTAT651 for biostat students
Description: The goal of this pilot course is to create an interdisciplinary educational experience for Ph.D. students in Epidemiology (also available as an optional elective for Masters students in Biostatistics) through a uniquely designed course that contains lectures on advanced biostatistical methods, but places them in the context of epidemiological applications.
Course Goals: Students enrolled in the class will learn about cutting edge statistical methods in these four contemporary topics that arise frequently in the present scientific context. These four topics are: (a) Modern techniques for model building and variable selection; (b) Methods for analyzing longitudinal data; (c) Spatial regression methods; (d) Methods for studies of interaction/effect modification. The course will equip the new generation epidemiologists with state-of-the-art statistical methods in these domains, and teach them the craft of translating a practical problem into mathematical equations. However, the entire theoretical learning process will be placed in the context of sophisticated modeling of data from large complex studies with a focused problem to solve. Data for the projects will come from two studies that Professors Park and Mendes de Leon are involved with: the Normative Aging Study (NAS) and the Chicago Health and Aging Project (CHAP).
Competencies: After completing this class, students are expected to be able to attain the following competencies:
-Describe preferred methodological alternatives to commonly used statistical methods when assumptions are not met.
-Distinguish among the different measurement scales and the implications for selection of statistical methods to be used based on these distinctions.
-Apply descriptive techniques commonly used to summarize public health data.
-Apply common statistical methods for inference.
-Apply descriptive and inferential methodologies according to the type of study design for answering a particular research question.
-Interpret results of statistical analyses found in public health studies.
-Develop knowledge to communicate and collaborate effectively with scientists in a variety of health-related disciplines to which biostatistics are applied (e.g. public health, medicine, genetics, biology; psychology; economics; management and policy).
-Become well-versed in the application of core statistical techniques (biostatistical inference, linear regression, generalized linear models, nonparametric statistical methods, linear mixed models) and 4-5 selected statistical specialization techniques.
-Select appropriate techniques and apply them to the processing of data from health studies.
-Interpret the results of statistical analysis and convert them into a language understandable to the broad statistical community.
-Develop written and oral presentation skills and other scientific reporting skills, based on statistical analyses for public health, medical and basic scientists and educated lay audiences
-Employ state-of-the-art statistical and other quantitative methods in the analysis of epidemiologic data.
-Demonstrate a thorough understanding of causal inference, sources of bias, and methods to improve the validity of epidemiologic studies.
-Understand the principles and methods of data-collection and data-processing procedures in the design and conduct of epidemiologic research, with sound knowledge of measurement validity and reliability, data quality control, data management, documentation, and security