Explanation of estimates

Estimates derived from a forecast of the data. The first estimate is a two-month ahead forecast of the data. When an additional month of data become available, BTS uses the data to re-forecast the month and releases a second estimate. BTS performs the forecasting using the Census X-12 procedure in SAS – a statistical software program.

Explanation of seasonal adjustment

When the primary purpose is to examine monthly shifts in transportation services output and analyze short-term trends, the variation introduced by normal seasonal changes must be removed from the data. Transportation is highly seasonal, and without adjustment, the data do not give an accurate picture of underlying changes in aviation, passenger travel.

Seasonal adjustment of the data removes the seasonal events that follow a regular seasonal pattern. Changes that are not due to seasonality, such as a change in air travel resulting from economic conditions become more readily apparent.

The aviation data are seasonally adjusted for the effects of trading day, moving holidays, and data outliers.

See Seasonal Adjustment  for methodology and additional explanation.

Seasonally-adjusted trends are for the time period January 2000 to present based on data reported by U.S. airlines through December and BTS estimates for the two most recent months. Additional data, including domestic and international numbers, can be found on the seasonally-adjusted data  page.

Unadjusted trends are for the time period January 1996 to present based on data reported by U.S. airlines through December and BTS estimates for the two most recent months. Data through December are available at Customize Table. Reported data and estimates for the two most recent months can be downloaded from the seasonally-adjusted data  page.