Housing price indices from online listing data: Addressing the spatial bias with sampling weights

Abstract

This paper proposes a method to reduce the inherent sampling bias when estimating housing price indices using online listing data. Producing more accurate and representative metrics is important as new sources of data emerge with higher frequency, detail, and volume, providing more information for policymaking, but usually come with strong sampling biases that are often overlooked. In the case of housing price indices, although the literature around its estimation is abundant, it has concentrated only in traditional and formal sources of housing data, which is normally not available in some markets (i.e. renting) and locations (developing countries). In this paper, I propose a method to create a housing price index (HPI) that is comparable in quality to the industry-standard Case-Shiller HPI but using online listing data. Using online listing data from a developing economy (Chile), this paper shows that large sampling biases present when using raw unweighted data, how these biases can be minimized using sampling weights, and how new and relevant information can be obtained from adjusted HPIs that can lead better policymaking.