What Drives the Difference between Online and Official Price Indexes?

Abstract

This paper examines the associations between online price indexes and official statistics. First, we generate online CPI component sub-indexes, which are later aggregated to an Online Price CPI. This approach is applied to our unique dataset which contains about 3 million observations of online retail prices for consumer goods in Ukraine’s five largest cities. The data span over the period 2016m1 – 2017m12 and cover about 46% of Ukraine’s Consumer Price Inflation basket. We find that online inflation is generally consistent with official estimates, but the matching capability varies across sub-indexes. Although the differences can partially be explained by poor dataset coverage, we find that online prices may indeed represent new information that is not captured by official statistics.

Keywords

• online prices
• web scraping
• consumer price index
• micro prices
• big data