Fitting Statistical Models to Data Using Python

In this course, we will expand our study of statistical inference methods by focusing on the art and science of fitting statistical models to data. We will build on concepts introduced in Statistical Inference (Course 2) to emphasize the importance of linking research questions and data analysis methods. We will also focus on the various purposes of modeling, including making inferences about relationships between variables and making predictions for future observations. This course will introduce and explore a variety of statistical modeling methods, including linear regression, logistic regression, generalized linear models, hierarchical and mixed-effects (or multilevel) models, and Bayesian inference methods. All methods will be illustrated on a variety of real-world data sets, and the course will emphasize different modeling approaches for different types of data sets, depending on the research design underlying the data (refer to Course 1, Understanding and Visualizing Data with Python). During labs, students will work through tutorials focused on specific examples to help reinforce the week's statistical concepts, which will include further in-depth exploration of Python libraries including Statsmodels, Pandas, and Seaborn. This course uses the Jupyter Notebook environment within Coursera.