Reference no: EM133165933

SOUTHWEST AIRFARES

Several new airports have opened in major cities, opening the market for new routes (a route refers to a pair of airports), and Southwest has not announced whether it will cover routes to/from these cities. In order to price flights on these routes, a major airline collected information on 638 air routes in the United States. Some factors are known about these new routes: the distance traveled, demographics of the city where the new airport is located, and whether this city is a vacation destiny. Other factors are yet unknown (e.g., the number of passengers that will travel this route). A major unknown factor is whether Southwest or another discount airline will travel on these new routes. Southwest's strategy (point-to-point routes covering only major cities, use of secondary airports, standardized fleet, low fares) has been very different from the model followed by the older and bigger airlines (hub-and-spoke model extending to even smaller cities, presence in primary airports, variety in fleet, pursuit of high-end business travelers). The presence of discount airlines is therefore believed to reduce the fares greatly. The file SouthWest.xlsx contains real data that were collected for the third quarter of a year and also the variable names (both response or dependent and predictor or independent) and definitions

1. Explore the numerical predictors and response (FARE) by creating a correlation table and examining some scatter plots between FARE and those predictors. 
2. What seems to be the best single predictor of FARE? 
3. Comment on multicollinearity using VIF values for all variables.
4. Find a model for predicting the average fare on a new route. Partition the data into training (60%) and validation sets (40%). The model will be fit to the training data and evaluated on the validation set. 
5. Perform a regression analysis using all the predictors. You can ignore the first four predictors (S CODE, S CITY, E CODE, E CITY). Remember to turn categorical variables (e.g., SW) into dummy variables first. Report the selected estimated model.
6. Use stepwise regression to reduce the number of predictors. You can ignore the first four predictors (S CODE, S CITY, E CODE, E CITY). Remember to turn categorical variables (e.g., SW) into dummy variables first. Report the selected estimated model. If you are using StatTools, use its 'Stepwise' feature instead of the default 'Multiple'. Note: If for software accessibility reasons you cannot use stepwise regression, you may remove the insignificant explanatory variables from model (b) and run the regression to get model (c).
7. Compare the predictive accuracy of both models (b), (c) using measures such as RMSE, Mean Error, MAD, and MAPE. 
8. Using model (c), predict the average fare on a route with the following characteristics: COUPON=1.202, NEW=3, VACATION=No, SW=No, HI=4442.141, S INCOME = $28,760, E INCOME=$27,664, S POP=4,557,004, E POP=3,195,503, SLOT=Free, GATE=Free, PAX=12782, DISTANCE=1976 miles. What is a 95% predictive interval? 
9. Predict the reduction in average fare on the above route if Southwest decides to cover this route (using model (c)).