The Port of Oakland airport reports the number of passengers passing through each month. At first glance, this is just simple growth, but by recognizing the series as a time series, we may learn more. The following plot was created in Excel 2013.

The increasing spread of the data suggests that a multiplicative model may fit better.
Here€™s an exponential trend model with seasonal (monthly) dummy variables.

a) Interpret the slope.
b) Interpret the intercept.
c) Which months have the lowest traffic at Oakland airport?
Here€™s a plot of the residuals from the model fit to the Oakland airport passengers, created in Excel:

d) What components would you now say are in this series?

Transcribed Image Text:

1500000 1300000 1100000 500000 700000 500000 300000 12 16 Years since 1990 Dependent variable is: LogPassengers R squared# 92.4% R squared (adjusted)#91.9% s 0.0358 with 194-13-.181 degrees of freedom Variable Intercept Years since 90 0.024929 0.0006 Feb Mar Apr May SE (Coeff) t-ratio P-value 0.0001 45.2 <0.0001 -1.10 0.2747 3.82 0.0002 3.93 0.0001 5.30 <0.0001 6.54 <0.0001 7.52 <0.0001 9.61 <0.0001 2.32 0.0216 3.91 0.0001 3.13 0.0020 3.44 0.0007 Coeff 5.64949 0.0101 558 -0.013894 0.0127 0.048429 0.0127 0.049028 0.0125 0.066227 0.0125 0.082862 0.0127 0.095295 0.0127 0.121779 0.0127 0.029382 0.0127 0.049596 0.0127 0.039649 0.0127 0.043545 0.0127 un Jul Aug Oct Nov Dec 0.1 0.05 트 005 0.1 015 12 16 Years Since 1990