Art Markets: Paris Paintings

Project Summary

What drove the prices for paintings in 18th Century Paris?

Themes and Categories
Year
Contact
Paul Bendich
bendich@math.duke.edu

Graduate students: Hilary Cronheim and Sandra van Ginhoven, Duke Art, Law and Markets Initiative-DALMI

Faculty instructor: Mine Çetinkaya-Rundel

Course: STA112FS Better Living Through Data Science: Exploring/Modeling/Predicting/Understanding

What drove the prices for paintings in 18th Century Paris?

  • Auction price data
  • Visual characteristics of paintings
  • Sales information
  • Art dealers’ strategies

Methods used:

  • Data exploration
  • Variable interactions
  • Model fit and selection
  • Interaction variables
  • Prediction

Related Projects

Large publicly available environmental databases are a tremendous resource for both scientists and the general public interested in climate trends and properties. However, without the programming skills to parse and interpret these massive datasets, significant trends may remain hidden from both scientists and the public. In this data exploration, students, over the course of three hours, accessed two large, publicly available datasets, each with greater than 4 million observations. They learned how to use R and RStudio to effectively organize, visualize and statistically explore trends in deep sea physical oceanography.  

Our aim was to introduce students to the wealth of possibilities that human genotyping and sequencing hold by illustrating firsthand the power of these datasets to identify genetic relatives, using the story of the Golden State Killer’s capture with public genetic databases.

This Data Expedition introduced hypothesis-driven data analysis in R and the concept of circular data, while providing some tools for importing it and analyzing it in R.