Qualitative Methods

Filtering, Visualizing, and Interpreting Spatial Time Series Data

December 17, 2025
by Maksymilian Jasiak. Spatial time series (consecutive measurements across space and time) are often difficult to interpret, especially when there are many overlapping signals. However, have no fear! Filtering and visualizing can help better interpret and understand the spatial time series data.

Digitization of Historical Maps in the Age of AI

December 3, 2025
by Elena Stacy. Researchers today increasingly have access to a wealth of tools to streamline or automate labor-intensive data processing and generation tasks. When it comes to mapping, progress has been slower. This blog details the author's experience tackling the digitization of a historical map in the age of AI.

Sahiba Chopra

Data Science Fellow 2024-2025
Haas School of Business

I'm a PhD student in the Management and Organizations (Macro) group at Berkeley Haas. I have a diverse professional background, primarily as a data scientist across numerous industries, including fintech, cleantech, and media. I hold a BA in Economics from the University of Maryland, an MS in Applied Economics from the University of San Francisco, and an MS in Business Administration from UC Berkeley.

My research focuses on the intersection of inequality, technology, and the labor market. I am particularly interested in understanding how to reduce inequality in...

A Participant-Centered, GIS-Based Approach to Improving Contextual Measurement

November 19, 2025
by Sarah Daniel. Researchers increasingly recognize that neighborhoods profoundly shape life outcomes, yet measuring them remains challenging. A common approach uses administrative boundaries, such as census tracts, as proxies for neighborhoods, but this method presents three key challenges. First, administrative boundaries may fail to capture residents’ lived experiences, a limitation that is particularly concerning in marginalized communities; second, they can misrepresent contextual effects; and third, they may produce inconsistent findings. To address these issues, I advocate for the use of self-defined neighborhood boundaries as an alternative measure. I compare GIS- and non-GIS-based methods and propose that GIS-based methods offer the strongest potential for more valid measurement.

Beyond the Hype: How We Built AI Tools That Actually Support Learning

November 12, 2025
by Weiying Li. What does genuine partnership look like when building AI for education? Working with middle school teachers and computer scientists, we co-designed AI dialogs where teachers are valuable contributors to refine what the AI understands as valuable thinking. Through iterative refinement, teachers identified precursor ideas and observations that predicted future learning, and refined guidance design in the dialog. Our AI dialog sees learning the way teachers do, built through genuine collaboration where both model development, learning sciences theories, and teachers' classroom expertise work together from the start, not just at the end.

Yaxuan Huang

Consulting Drop-In Hours: By appointment only

Consulting Areas: Causal Inference, Git or GitHub, LaTeX, Machine Learning, Python, Qualitative Methods, R, Regression Analysis, RStudio

Quick-tip: the fastest way to speak to a consultant is to first submit a request and then ...

Umesh Singla

Consulting Drop-In Hours: By appointment only

Consulting Areas: Bash or Command Line, Bayesian Methods, Causal Inference, Data Visualization, Deep Learning, Diversity in Data, Git or GitHub, Hierarchical Models, High Dimensional Statistics, Machine Learning, Nonparametric Methods, Python, Qualitative Methods, Regression Analysis, Research Design

Quick-tip: the fastest way to speak to a consultant is to first ...

Sharazad Ali

Consulting Drop-In Hours: By appointment only

Consulting Areas: Cluster Analysis, Databases and SQL, Data Visualization, Diversity in Data, Excel, Experimental Design, Focus Groups and Interviews, Machine Learning, Means Tests, Python, Qualitative Methods, Qualtrics, R, Regression Analysis, RStudio Cloud, Software Output Interpretation, SQL, Time Series

Quick-tip: the fastest way to speak to a consultant is to first ...

Alyssa Heinze

Consulting Drop-In Hours: By appointment only

Consulting Areas: Causal Inference, Data Visualization, Experimental Design, Focus Groups and Interviews, Git or GitHub, LaTeX, Machine Learning, Meta-Analysis, Mixed Methods, Qualitative Methods, Qualtrics, R, Regression Analysis, Research Design, RStudio, STATA, Survey Design, Text Analysis

Quick-tip: the fastest way to speak to a consultant is to first ...

John Louis-Strakes Lopez

Postdoctoral Scholar
Berkeley School of Education

John Louis-Strakes Lopez is a Data Science Education postdoctoral scholar. He recently received his PhD in Education from University of Caifornia, Irvine. John’s work looks at student epistemological development within data science contexts. He is also interested in designing -and studying artificial intelligence and playful learning technologies for learning. John serves as a co-chair for the International Learning Sciences Student Association.

Beyond work, you will find John reading at a local coffee shop or eating a warm bowl of Pho.