The Analysis of Tribal Art Prices: a Multilevel Model with Autoregressive Components

TL;DR

This paper introduces a novel multilevel model with autoregressive components for analyzing auction prices of tribal artworks, effectively handling the unique data structure of repeated cross-sections and improving fit and prediction.

Contribution

It develops a new multilevel model with time series components and full maximum likelihood estimation via the E-M algorithm for tribal art price analysis.

Findings

Model significantly improves fit over existing methods

Enhanced prediction accuracy for tribal art prices

Effective handling of repeated cross-sectional auction data

Abstract

In this paper we propose a multilevel model specification with time series components for the analysis of prices of artworks sold at auctions. Since auction data do not constitute a panel or a time series but are composed of repeated cross-sections they require a specification with items at the first level nested in time points. An original feature of our approach is the derivation of full maximum likelihood estimators through the E-M algorithm. The data analysed come from the first database of ethnic artworks sold in the most important auctions worldwide. The results show that the new specification improves considerably over existing proposals both in terms of fit and prediction.