Activity Number:
|
649
- The 'Ergonomics' of Statistics and Data Science
|
Type:
|
Invited
|
Date/Time:
|
Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
|
Sponsor:
|
International Statistical Institute
|
Abstract #326821
|
|
Title:
|
How Human Behavior Drives Data Science---and How We Know Almost Nothing About It
|
Author(s):
|
Jeffrey Leek*
|
Companies:
|
Johns Hopkins Bloomberg School of Public Health
|
Keywords:
|
data science as a science;
data analysis;
human factors research;
data science
|
Abstract:
|
Most of what happens in a data analysis is a choice by a human. For very specific subfields we have some information on good and bad choices humans can make, but we don't have much information on how to deal with human choices throughout the analytic pipeline. These "researcher degrees of freedom" are one of the major culprits for the reproducibility crisis. I'll discuss our efforts to design data science as a science and our experiments to try to understand the human behavior involved in data analysis.
|
Authors who are presenting talks have a * after their name.