This workshop will cover fitting generalized linear models (GLMs) in Python, using the Statsmodels package.  We will cover logistic regression, but the majority of the time we will focus on other GLMs including Poisson, negative binomial, and gamma regression.  We will provide an overview of the underlying foundation for GLMs, focusing on the mean/variance relationship […]

In this session, we will discuss fitting traditional regression models in Stata, including linear regression, logistic regression, and time-allowing, poisson regression. We'll briefly introduce the theory behind the models, discuss choosing an appropriate model, fitting the model, checking assumptions and some post-hoc analysis. Participants are expected to have some basic familiarity with Stata.

Video game development is more accessible than ever thanks to advanced software tools. Unity3D is one of the most popular game engines available, thanks to its ease of use, support for multiple platforms, and affordable pricing options (including free!). In addition to powering the majority of mobile and independently-developed games, the engine is being used […]

GEE is an extension of the generalized linear modeling (GLM) framework for dependent data.  GEE can be used with longitudinal data, clustered data, and other forms of dependent data where a GLM may not be appropriate.  In this workshop we will discuss fitting models using GEE in Python with the Statsmodels package.  We will briefly cover […]

This is a four-part workshop introducing programming concepts to those with little-to-no programming experience. The four 2-hour sessions will take place over two weeks, with Python being taught in the first three sessions, and Matlab in the fourth session. Computers are provided. Session 1: Feb 6, 11am - 1pm - Location: MLB 2001a Session 2: […]

Mixed models are an extremely useful modeling tool for situations in which there is some dependency among observations in the data, where the correlation typically arises from the observations being clustered in some way. For example, it is quite common to have data in which we have repeated measurements for the units of observation, or […]

We'll discuss mixed model regression (also known as multi-level models or hierarchical linear models) in this session which is used for repeated measures data or data which has a clustering element.  We'll start with a theoretical overview, discuss choosing an appropriate model, fitting the models, checking assumptions and post-hoc analysis. We'll also cover diagnosing convergence […]

Learn data analysis with Python. We’ll be using pandas, the go-to Python library used for data wrangling and analysis. We’ll be practicing with several different real-world datasets (e.g. time-series, text) and learning how to read, write, clean, transform, merge and reshape data. The workshop is intended for users with basic Python knowledge. Anaconda Python 3.6 […]

Multilevel modeling is the state-of-the-art approach for handling data with complex dependence structure in a regression analysis.  This workshop will discuss fitting multilevel models in Python using the Statsmodels package. We will discuss the motivation and main use cases for multilevel modeling, and illustrate by example how to fit linear and generalized linear mixed models. […]

Survival analysis is used when working with data that may be censored, as often is the case in studies of human subjects with incomplete follow-up.  The presence of censoring makes most forms of regression and other standard statistical analyses inappropriate. A body of specialized techniques for analyzing this type of data has been developed, including […]

Nonlinear relationships abound in nature, though typical statistical models ignore this in favor of simplicity, often at a cost of both predictive capabilities and better understanding of the underlying phenomenon of interest.  One means to explore such relationships is through generalized additive models (GAM). This workshop will introduce participants to GAMs as a means to […]

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification […]

Google Earth Engine combines a multi-petabyte catalog of satellite imagery and geospatial datasets with planetary-scale analysis capabilities. This hands-on workshop will help you understand the power (and limitation) of GEE for carrying out an end-to-end analysis. You should have some exposure to GEE and remote sensing. We will focus on contemporary environmental issues and learn […]