This workshop will show how descriptive analyses, both numerical and graphical, can be done with continuous and categorical variables. Subpopulation analysis will be discussed and then examples of OLS regression and logistic regression will be considered. Survey Data Analysis with R
While machine learning methods have traditionally been used for prediction in fields like industry and technology, they are increasingly being adopted in scientific research for exploration and inference. This two-part workshop introduces key machine learning techniques used for scientific applications. Part 1 discusses core concepts such as prediction accuracy, the bias-variance tradeoff, and cross-validation. Part 2 introduces commonly used methods for scientific research, including ridge regression, LASSO, principal components analysis (PCA), regression trees, and random forests. Practical examples and demonstrations will be provided using R, and we will discuss how these tools can complement traditional statistical approaches in scientific research. No prior experience with machine learning is required, though familiarity with basic regression is recommended. Machine Learning for Scientific Research. Part 2
This workshop introduces the functionality of Stata with a focus on data analysis. We will discuss the basic interface and do-files as well as explore commands to import data, create and modify variables, summarize variables, visualize data, combine data sets, and to run basic analyses. No experience with Stata is assumed. Introduction to Stata