2,644,539

2,359,800

2,925,918

3,024,973

3,177,100

3,419,595

3,649,702

3,650,668

3,191,526

3,249,428

2,971,484

3,074,209

2,785,466

2,515,361

3,105,958

3,139,059

3,380,355

3,612,886

3,765,824

3,771,842

3,356,365

3,490,100

3,163,659

3,167,124

2,883,810

2,610,667

3,129,205

3,200,527

3,547,804

3,766,323

3,935,589

3,917,884

3,564,970

3,602,455

3,326,859

3,441,693

3,211,600

2,998,119

3,472,440

3,563,007

3,820,570

4,107,195

4,284,443

4,356,216

3,819,379

3,844,987

3,478,890

3,443,039

3,204,637

2,966,477

3,593,364

3,604,104

3,933,016

4,146,797

4,176,486

4,347,059

3,781,168

3,858,196

3,562,680

3,633,798

As a manager of a regional airport, you need to forecast monthly passenger flow (number of passengers flying in and out) through the airport for planning and budgeting purposes. You have historical monthly airport passenger data over last five years - ending in December 2022 (above dat). You want to explore the idea of exponential smoothing to model the history and prepare forecast for next year (January 2023 to December 2023).

(a) Plot the historical data over time and decide what exponential smoothing model(s) are appropriate to try to model the historical behavior.

(b) Use SPSS to fit all the models you identified in Step (a) and forecast monthly passenger flow this airport can expect for next year. For each model, interpret values of all relevant statistics (RMSE. MAPE, MAE, etc.).

(c) Among all the models you tried in Part (b), discuss which model (and associated forecast) you will use (and why?) to predict the monthly passenger flow at this airport for next one year. How good do you think is your forecast?