PM: Data analysis demos at Green Library
Data analysis demos at Green Library, Velma Denning Room, 120F
Friday, October 19, 2018
Reproducible research with R
with Claudia Engel
The goal of reproducible research is to improve scholarship by documenting data, code, and methods so results can be replicated and be subjected to scrutiny. R supports reproducible research through the creation of documents that combine content and code. This session will provide an overview of how to generate these documents and review some of the relevant R packages.
Claudia Engel is Academic Technology Specialist and Lecturer for the Department of Anthropology and member of the Center for Interdisciplinary Digital Research at the Stanford Libraries. She collaborates with Anthropology faculty on innovative technology projects that are part of their research and teaching. She also teaches and co-teaches Anthropology courses.
Qualitative research tools: NVivo, RQDA, Python
with Alesia Montgomery
Are you doing a qualitative analysis of “unstructured data” (e.g., interview transcripts, government documents, observational videos)? This demo will show three tools:
- Commercial software: NVivo (free to Stanford faculty, students, staff)
- Open source software: RQDA (free to all—an R package)
- Programming language: Python (free to all)
Come find out the basics about (1) how to choose the right tool for you (e.g., based on your epistemological assumptions, research questions, dataset size/type, data management needs), (2) how to get these tools, and (3) how to use these tools to qualitatively “code” your data. The workshop will include information about Stanford resources for learning how to use these tools.
Alesia Montgomery is the Subject Specialist for Sociology, Psychology, and Qualitative Data at Stanford. For over two decades, she has been engaged in qualitative research and teaching. Her publications include articles in International Journal of Urban & Regional Research, City & Community, Global Networks, and Ethnography.
Computational text analysis in the social sciences: “Analyzing bias in college admissions essays”
with AJ Alvero, Graduate Student, Stanford Graduate School of Education
College admissions essays (CAE) are a prominent yet understudied aspect of the college admissions process. As more schools drop SAT/ACT requirements for admissions, their role will become even bigger. This study uses machine learning methods to understand the relationship between essay content (what students are writing about) and social context to explore potential bias in the CAE genre.
AJ Alvero is a PhD candidate in the Stanford University Graduate School of Education in the educational linguistics and Race, Inequality, and Language in Education (RILE) programs. His research lies at the intersection of AI, language, and education with the goal of improving educational equity and outcomes for all. AJ was born and raised in Salinas and earned a BA in English from the University of Miami and an MS in foreign language education (TESOL) from Florida International University in Miami, FL.