Real-Time Forecasts of Auction Prices

30 Pages Posted: 26 Feb 2020

Date Written: October 5, 2014


This paper investigates the informational content of aggregate prices in the fine arts auction market. A Mixed Data Sampling (MIDAS) modeling approach is proposed to forecast year-end art prices, using higher frequency variables related to the stock and bond markets and to art market sentiment. It takes about six months for art prices to incorporate information contained in the price of Sotheby's stock. Market sentiment variables such as trading volume have better explanatory power in the short-term. These findings suggest that art market participants react with a delay to information contained in stock market returns, so that information diffuses only slowly into art prices.

Keywords: Information and market efficiency; MIDAS; Information diffusion; Art auctions; Forecasting; Market sentiment.

JEL Classification: C58, G12, G14, Z11.

Suggested Citation

Pénasse, Julien, Real-Time Forecasts of Auction Prices (October 5, 2014). Available at SSRN: or

Julien Pénasse (Contact Author)

University of Luxembourg ( email )

4 Rue Albert Borschette
Luxembourg, L-1246

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
PlumX Metrics