Workshop Instructors

Fall 2023 Workshop Instructors

If you have questions regarding any of the workshops, please reach out directly to the instructor.

Kyung-Hae Bae

Kyung-Hee Bae
Director, Center for Academic & Professional Communication
Website

Effective Research Presentations

Workshop information coming soon.


Catherine R. Barber

Catherine R. Barber
Associate Director and Assistant Teaching Faculty
Center for Teaching Excellence
Website

Introduction to R

This workshop introduces R and RStudio, with an emphasis on analyzing and visualizing quantitative data. Participants will learn to examine and modify datasets, index and transform dataframes, calculate descriptive statistics, and create basic plots in R. No programming experience is needed!

Prerequisites

Familiarity with descriptive statistics and the essentials of statistical hypothesis testing is recommended. Participants will need to bring their own device with R and RStudio pre-installed. Installation instructions and suggested readings will be available on Canvas prior to the workshop.


Roberto Bertolusso

Roberto Bertolusso
Senior Pfeiffer Lecturer, Department of Statistics
Website

Intermediate R

Workshop information coming soon.


Flavio Cunha

Flávio Cunha
Ervin K. Zingler Chair of Economics
Department Chair, Economics
Website

Sample Selectivity and Estimation of Counterfactual Distributions

Workshop Description: This workshop discusses conducting program evaluations when individuals are not randomly assigned to a social program or medical treatment. We will discuss how to model these situations and the benefits and costs of such an approach. In particular, we will apply this model to a case when individuals are randomly assigned to a group, but adherence to the experimental protocol is imperfect (thus, there is sample selectivity).

Prerequisites

Familiarity with estimation of linear regression models and models with discrete dependent variables (e.g., logit, probit).


Bryan Denny

Bryan Denny
Assistant Professor, Psychological Sciences
Website

fMRI Methods in Cognitive Neuroscience

Workshop information coming soon.


Christina Diaz

Christina Diaz
Assistant Professor of Sociology
Website

Introduction to Linear Models

The purpose of this seminar is to familiarize attendees with basic statistical operations so that they can read, understand, and evaluate quantitative research. We will begin with a review of basic statistics (estimates/uncertainty, hypothesis testing) and move on to focus on the linear regression model, which is the workhorse of quantitative social science. Specifically, we will use linear regression to examine how observed characteristics can predict important outcomes in the social world—such as wages. We will then focus on interpreting and showcasing our results.

Prerequisites

undergraduate statistics; or review of supplemental material provided by the instructor. The use of a scientific calculator (e.g. TI-30) is encouraged for working through workshop material.


Shani Evans

Shani Evans
Assistant Professor of Sociology
Website

Data Collection via In-Depth Interviewing

This workshop will be beneficial for those who are interested in qualitative interviewing as a method of data collection. We will review examples of interview research and learn about the types of research questions that are well suited for qualitative interview studies. We will discuss research design for qualitative interview studies, including sampling, recruitment, writing the questionnaire, and developing an analytical strategy. Participants will also learn strategies for conducting effective interviews.


Jeremy Fiel

Jeremy Fiel
Assistant Professor, Department of Sociology
Director of Graduate Studies
Website

Synthetic Control Group Designs Using Stata

To test hypotheses or evaluate the effects of policies or events, quantitative research seeks good comparisons. When randomized experiments are not an option, quasi-experimental methods are often the next best thing, creating “treatment” and “control” groups that are as comparable as possible in the absence of the event or policy of interest. With observational data, sometimes there is no single ideal control group, but we can piece together a very good “synthetic control group” from a pool of candidates. In this workshop, students learn to use STATA to build a synthetic control group that can be incorporated into a variety of research designs. It also shows how to pair this approach with an interrupted time series design in which we observe cases before and after some event of interest. The workshop uses data from a study evaluating the unintended effects of a change in states’ college admissions policies on high school segregation. Data and code will be provided in STATA.

Prerequisites

Students should have an understanding of basic statistics and linear regression. A computer with a working version of STATA is necessary to work in real-time, but is not required to participate.


Luz Maria Garcini

Luz Maria Garcini
Assistant Professor, Department of Psychological Sciences
Website

Mixed Methods for Diversity Health Research

This workshop will provide an introductory overview on the use of mixed methods research for working with historically underrepresented and marginalized communities. At the conclusion of the workshop, attendees will be able to:

  • Understand the need for and importance of mixed methods for diversity research
  • Learn to identify a topic and formulate scientific questions for mixed methods studies
  • Identify different types of mixed methods core study designs
  • Learn basic strategies for collecting, analyzing and interpreting mixed methods data
  • Understand the basics of writing mixed methods papers
Prerequisites

To get the most out of this workshop, it will be helpful for attendees to come prepared with a research idea that they could explore using mixed methods. Templates will be provided to outline your ideas using mixed-methods.


Edgar Avalos Gauna

Edgar Avalos Gauna
Lecturer, Department of Statistics
Website

Machine Learning

Machine learning, according to the IBM website's definition, is a branch of Artificial Intelligence (AI) which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. Most sources consider three different types of machine learning: Supervised, Unsupervised and Reinforcement learning. The goal of this workshop is to provide some of the fundamentals for some of the applications of machine learning: regression, classification, dimensionality reduction, and clustering.


Hua Gong

Hua Gong
Assistant Professor of Sport Management
Website

Introduction to Python

The workshop aims to teach participants how to use Python to perform data analysis. Three main topics of Python will be covered during the workshop. First, two widely used packages, Pandas and Numpy, will be introduced and detailed information on how to use them in data manipulation will be provided. Second, we will draw attention to data visualization in Python. The package Matplotlib will be used to create professional graphs, such as line and box plots, in Python. Lastly, we will discuss how to perform linear and logistic regression models by using the Scikit-learn package in Python. At the end of the workshop, students are expected to become familiar with Python and develop essential skills of using Python to perform data analysis.


Ibrahim Gumel

Ibrahim Gumel
Senior GIS Support Specialist, Fondren Library
Website

Introduction to ArcGIS Pro and GIS Data Management

Geographic Information Systems (GIS) enable users to visualize and analyze spatial information in a dynamic digital environment. This workshop will introduce students to general GIS concepts and applications. Participants will become familiar with the ArcGIS Pro environment and will gain hands-on experience using ArcGIS Pro to create a GIS project utilizing a variety of data layers.


Cymene Howe

Cymene Howe
Professor of Anthropology
Website

Ethnographic Techniques I

This workshop is an introduction to the art and science of observing, documenting and analyzing cultural forms. Among qualitative research methods, ethnographic approaches are exceptional in their detail, illustrative capacities and ability to highlight the voices of everyday folk and the complexities of their lives. In this workshop we will overview participant observation, interviewing techniques, field notation and ethnographic writing and we will engage with the complexities of decolonizing representation.

Prerequisites:

Prior to the workshop, please find (and bring) a piece of descriptive writing--a paragraph or two--that you find especially compelling. It can be any genre: literary, social scientific, journalistic, etc. Please also bring to class a small notebook or pad of paper and pen or pencil.


Jing Li

Jing Li
Adjunct Associate Professor of Sociology
Website

Introduction to Multilevel Modeling

This applied course introduces the basic concepts and applications of multilevel models, also known as hierarchical linear models or mixed models. The course will start with an introduction of nested data and common methods of analyzing such data, followed by a discussion about the advantages of using multilevel modeling methods. It will focus on contextual analysis (e.g. neighborhood effects research, school effect research) with an emphasis on conceptual understanding and interpretation of results. Both Stata and R codes will be discussed.

Prerequisites:

A good understanding of descriptive statistics, significance testing, bivariate regression, multivariate regression and generalized linear models. Basic knowledge of Stata or R is preferred but nor required.


Victoria Massie

Victoria Massie
Assistant Professor of Anthropology
Website

Empowered Illness Narratives, Rewriting Health Inequalities

This workshop is an introduction to how the art of storytelling can help us reimagine the human aspects of illness for doctors and patients and speculate interventions into the structural conditions that predispose people to being sick. Drawing on ethnographic methods of social discourse analysis, this workshop aims to get participants to open up our diagnostic sensibilities about what makes individuals, groups, and societies sick. We will address interviewing techniques, developing a questionnaire, media analysis, and explore experimental techniques such as collaging and creative writing to recent people at the heart of redressing health inequalities.

Prerequisites

In preparation for the workshop, participants should pick a health disparity that they want to focus on. Once that health disparity has been identified, participants should bring two to three different discussions of the disparity (for instance, scientific papers, newspapers, social media, film, TV, etc), one of which should be a personalized story (not necessarily that of the participant). Lastly, participants should include an image/photo tied to the health disparity.


John Mulligan

John Mulligan
Humanities Computing Researcher/Facilitator, Center for Research Computing
Digital Scholarship Postdoctoral Fellow, Center for Research Computing
Website

Designing and Deploying a Data Visualization App

This workshop will introduce you to:

  • Exploratory Data Analysis
  • Programming Python in Jupyter notebooks
  • Setting up virtual environments for Python
  • Using git to control and to share your code
  • Critically analyzing data visualizations
  • Running a data visualization app using Plotly
  • Deploying a data visualization app in the cloud

We will update this code and push it to the cloud.

My goal is to introduce you to the basics of building a data visualization dashboard, from beginning to end, and to set you up with the tools you need to do this on your own. You will leave the class with working tools and a working knowledge of what’s going on under the hood of some of these slick data dashboards that are proliferating in the age of big data and cloud computing.

You can view the full lesson plan here: https://github.com/johnmulligan/covid_dashPy

We will use Python notebooks to load a CDC COVID dataset, and to sandbox different ways of visualizing it using the data visualization framework Plotly.

We will critically evaluate some existing visualizations of the dataset. How interactive can we make this data? What does interactivity show us about this dataset? And can something be too interactive?

We will set up an environment on your system that allows you to run a web app visualizing this data in a different way.

We will explore the code that runs it.

Prerequisites

Pre-class software installations in the lesson plan: https://github.com/johnmulligan/covid_dashPy#i-pre-class-installations


Hoang Nguyen

Hoang Nguyen
Associate Professor, School of Nursing
The University of Texas Medical Branch at Galveston
Website

Using Electronic Medical Records in Public Health Research

In this workshop we will define what is EMR and how it can be used to conduct public health research. We will present an overview of what data are captured in EMR databases and how the data are organized. We will then dive into the research uses of EMR with real-world examples. In the second part of the workshop, we will conduct a mock research project using EMR starting with framing the research question, identifying the variables, and creating an analytical data file. We will then analyze the data and interpret the results.


Fred Oswald

Fred Oswald
Herbert S. Autrey Chair in Social Sciences and Professor of Psychology
Website

Conducting Meta-Analysis

Meta-analysis is one of the most popular statistical methods in the sciences for aggregating statistical effects in a wide variety of research disciplines, including (but certainly not limited to) the social sciences, medicine, education, and business. Although meta-analysis is motivated by a conceptual or theoretical framework, actually conducting the meta-analysis requires identifying, sifting, combining, analyzing, comparing, and interpreting effect sizes across a set of studies investigating the same (or similar) psychological phenomena. In short, meta-analysis is a process that requires a solid conceptual foundation and judicious decision making as much as (and perhaps more than) statistical skill. This course will walk you through this process: e.g., developing and using a coding sheet; understanding statistical artifacts (e.g., sampling error variance, measurement error variance); choosing between fixed-, random, and mixed-effects models; the visualization of heterogeneity and potential publication bias; and some extensions of basic meta-analysis models.

Prerequisites

Within your research area(s) of interest, please locate the PDF of one published meta-analysis that looks interesting to you, and please email me that foswald@rice.edu. Also, it is helpful (though not necessary) to bring a laptop with R and RStudio installed, to run analyses with me.


Anna Rhodes

Anna Rhodes
Assistant Professor of Sociology
Website

Coding and Memoing in Qualitative Analysis

This workshop introduces strategies for analyzing qualitative data, with a specific focus on coding techniques and approaches to memoing. We will discuss when to utilize these tools in a research study as well as a number of different ways to use coding and memoing to categorize, analyze, and summarize your qualitative data effectively. We will cover how to establish an iterative analytic strategy that integrates both coding and memoing. Finally, we will discuss the tools available to you in QDA (qualitative data analysis) software programs, and review examples in one of these programs.

Prerequisites

If you have collected your own qualitative data in any form, you may bring a sample of several pages to work with for practice. If not, example material will be provided for you.


Angela Thompson

Angela Thompson
Assistant Director of Survey Research, Office of Institutional Effectiveness
Website

Survey Design and Implementation via Qualtrics

This workshop is an introduction to the Qualtrics Survey Software (DesignXM product). The workshop will include:

  • Step-by-step instructions for creating a survey, disseminating the survey using various methods, exporting data, and viewing results
  • Overview of XM Directory
  • Qualtrics tips and tricks including custom coding to add a print button and how to hide the submit button to prevent survey submission (and why that may be necessary)
  • Useful but less commonly used survey features
  • Qualtrics review of survey methodology & compliance best practices
  • Examples of surveys and applications built using Qualtrics
  • An opportunity to create and administer your own survey
Prerequisites

Please bring a laptop with Microsoft Excel installed. To get the most out of this workshop, it will be helpful for attendees to come prepared with 5 sample survey questions and 5-7 test email addresses to use for developing and administering a survey during the workshop.


Matt Tyler

Matt Tyler
Assistant Professor, Department of Political Science
Website

Approaches to Recovering Missing Data

The goal of this seminar is to equip attendees with the skills to address the all-too-familiar problem of missing data. We will begin by discussing what missing data problems can and cannot be "fixed" with standard methods. We will then introduce the theory and practical implementation of multiple imputation as a general missing data solution. (Note: our focus will be on large-N cross-sectional or large-N/small-T panel datasets.)

Prerequisites
  • Comfort with linear regression models. Familiarity with generalized linear models or machine learning methods would help attendees but is not strictly necessary.
  • Comfort with R and R packages. Package installation instructions and example datasets will be available on Canvas prior to the workshop.
  • Comfort with statistical ideas like conditional dependence and independence. Comfort with conditional expectation and conditional variance, especially the law of total variance, would help attendees but is not strictly necessary.

Marina Vannucci

Marina Vannucci
Noah Harding Professor, Department of Statistics
Website

Bayesian Thinking and Analysis

Workshop information coming soon.


Miranda Waggoner

Miranda Waggoner
Associate Professor of Sociology
Website

Archival Methods for Health Research in the Social Sciences

This workshop introduces key approaches to archival methods in the social sciences, focusing particularly on research related to health and medicine. We will discuss the various kinds of archived sources and data that researchers may seek out and use in their work, and we will discuss multiple strategies for undertaking archival research. Using examples from both digital archives and physical archives, we will cover how to access, collect, and analyze archival sources/data, and we will consider how such work can add to, expand, and enrich conversations about contemporary issues and debates in health research. We will also examine the meaning of “the archive” and review ethical and practical considerations surrounding archival research.