Hedonic wine price functions and measurement error

Accumulated theoretical and empirical evidence suggests that wine prices depend on quality, reputation and objective characteristics. Unlike previous studies, we recognize that quality and reputation are latent constructs and therefore employ factor analysis and 2SLS techniques to consistently estimate hedonic prices in the presence of attributes measured with error. The application to Australian premium wines points to significant reputation effects but insignificant quality effects. It is also illustrated that inappropriately using standard OLS procedures can seriously distort the statistical significance of attributes, the implicit marginal attribute prices, and the predictions of 'average' prices for a given set of characteristics.