Price duration using daily online data: Time- or state-dependent?

Using daily retail prices gathered through web scraping in Mexico, we analyse time- and state-dependent price setting rules as determinants of the duration of price spells, or the probability of price changes. Through the lens of a duration model, we find some evidence of state-dependent behaviour, which suggests that sheer time-dependent pricing models are unable to fully describe the features of the data. Specifically, we find statistically significant impacts on the probability of a price change of the COVID-19 pandemic, of variations in the nominal US/MXN exchange rate and of variations of real point of sales expenditures. Finally, leveraging price data gathered via direct visits to brick-and-mortar stores, we find that the state of the economy has similar impacts on the expected duration of price spells across both websites and physical stores.