Google Econometrics: The Power of a Search Engine

The purposed project will extend the previous literature in several ways. First, we will focus on analyzing the eligibility of Google search data for forecasting tourist arrivals and overnight stays in Prague. We will check whether the predications based on Google searches are advantageous for policy makers and businesses operating in the tourism sector in Prague. Second, the project will developed Mixed-data sampling (MIDAS), which is able to ignore the traditional requirement that variables be presented at the same frequency. We give special attention to analyzing whether weekly Google Trends data can potentially improve forecasting performance when used with MIDAS regressions. We will assess whether biased search results can change the choice of undecided users, and if so, whether this change differs across different groups.