You have a 4-year panel of data from 2009--2012 on air fares for 1 287 di Butes across the European Union. Consider the following model of air fares log( Farea ) - Do + in log( Passengers. ) - Be Mikishare + 53 Distance, 1 61 1 2009, + 6: 12010. 81201/14 (FA) where: Fareit is the average one-way fare (EUROs) on route ? in year Passengersy is the average number of passengers per day on route ? in year till Mkt Sharey is the fraction of the market held by the biggest carrier ( ile a measure of market concentration) Distance; is distance (hundreds of km) for route Yr2009, is a dummy variable equal to 1 in the year 2009 and 0 otherwise Yr2010, is a dummy variable equal to 1 in the year 2010 and 0 otherwise $Yr2011, is a dummy variable equal to 1 in the year 2011 and 0 otherwise Using the information above, answer the following 4 questions. (i) Provide two (2) examples of the kinds of variables that could be captured by the term a, in this model. [2 marks] (ii) What is the crucial assumption we must make so that the random effects (RE) estimator is consistent? Under this assumption, why is RE preferred to Pooled OLS? [3 marks] (iii) Outline the main idea of the fixed effects (FE) transformation underlying the FE estimator. [2 marks] (iv) When using the FE estimator why should we drop the variable Distance? [1 mark]