Correspondence Bias - Publications - Faculty & Research

2023
Working Paper

Feature Importance Disparities for Data Bias Investigations

By: Peter W. Chang, Leor Fishman and Seth Neel

It is widely held that one cause of downstream bias in classifiers is bias present in the training data. Rectifying such biases may involve context-dependent interventions such as training separate models on subgroups, removing features with bias in the collection... View Details

Keywords: AI and Machine Learning; Analytics and Data Science; Prejudice and Bias

Citation

Read Now

2013
Article

Inflated Applicants: Attribution Errors in Performance Evaluation by Professionals

By: S. A. Swift, D. Moore, Z. Sharek and F. Gino

When explaining others' behaviors, achievements, and failures, it is common for people to attribute too much influence to disposition and too little influence to structural and situational factors. We examine whether this tendency leads even experienced professionals... View Details

Keywords: Evaluations; Correspondence Bias; Selection Decisions; Attribution; Prejudice and Bias; Selection and Staffing; Decision Choices and Conditions; Performance Evaluation; Cognition and Thinking

Citation

Read Now