How Do Analysts Understand and Verify AI-Assisted Data Analyses?

K Gu, R Shang, T Althoff, C Wang… - Proceedings of the CHI …, 2024 - dl.acm.org
Data analysis is challenging as it requires synthesizing domain knowledge, statistical
expertise, and programming skills. Assistants powered by large language models (LLMs) …

Understanding and supporting debugging workflows in multiverse analysis

K Gu, E Jun, T Althoff - Proceedings of the 2023 CHI Conference on …, 2023 - dl.acm.org
Multiverse analysis—a paradigm for statistical analysis that considers all combinations of
reasonable analysis choices in parallel—promises to improve transparency and …

[PDF][PDF] Is social research really not better than alchemy? How many-analysts studies produce “a hidden universe of uncertainty” by not following meta-analytical …

K Auspurg, J Brüderl - 2023 - osf.io
Starting with Silberzahn and Uhlmann (2015), many-analysts studies have become a
popular design to examine the robustness and credibility of scientific research. We argue …

How Robust are Educational Mobility Analyses to Researcher Analytical Decisions?

E Strömberg - 2022 - diva-portal.org
As robustness of social science is getting more attention, analytical choices have been
found to be more important than previously thought. This thesis investigates robustness of …

[PDF][PDF] Quantifying analytical heterogeneity: The impact of violating the random-effects model's independence assumption

D Scherer - 2023 - diglib.uibk.ac.at
Abstract In 2015, Silberzahn and Uhlmann (2015) introduced the concept of crowdsourcing
data sets to multiple researchers asking them to analyse the same hypothesis. Several other …