Over the course of a year, the size of the Nation's labor force, the levels of employment and unemployment, and other measures of labor market activity undergo sharp fluctuations due to such seasonal events as changes in weather, reduced or expanded production, harvests, major holidays, and the opening and closing of schools. Because these seasonal events follow a more or less regular pattern each year, their influence on statistical trends can be eliminated by adjusting the statistics from month to month. These adjustments make it easier to observe the cyclical and other nonseasonal movements in the series. In evaluating changes in a seasonally adjusted series, it is important to note that seasonal adjustment is merely an approximation based on past experience. Seasonally adjusted estimates have a broader margin of possible error than do the original data on which they are based, because they not only are subject to sampling and other errors but also are affected by the uncertainties of the seasonal adjustment process itself.
Since January 1980, national labor force data were seasonally adjusted with a procedure called X-11 ARIMA (Auto-Regressive Integrated Moving Average), which was developed at Statistics Canada as an extension of the standard X-11 method.
Beginning with data published for January 2003, the X-12-ARIMA program is used to seasonally adjust labor force series. This program includes all the capabilities of the Statistics Canada program and it introduces new features. Developed at the U.S. Census Bureau (Findley and others, 1988), X-12-ARIMA provides enhancements to (1) ARIMA time series modeling and model selection, (2) detection and estimation of outlier, trading day, and holiday effects, (3) post-adjustment diagnostics, and (4) seasonal and trend filter options.
The changes introduced into the CPS in 2003 affect the number of series that are directly seasonally adjusted. Prior to 2003, 182 series based on age, sex, industry, occupation, and other characteristics were directly seasonally adjusted; beginning in 2003, 116 series are directly seasonally adjusted. Eighty-one series were eliminated; most of these were related to industry and occupation. Fifteen aggregate series, previously derived from detailed series no longer seasonally adjusted, are now directly seasonally adjusted at the aggregate level.
At the beginning of each calendar year, projected seasonal adjustment factors are calculated for use during the January-June period. In July of each year, BLS calculates and publishes in Employment and Earnings projected seasonal adjustment factors for use in the second half of the year, based on the experience through June. Revisions of historical data, usually for the most recent 5 years, are made only at the beginning of each calendar year.
Next: Presentation and Uses
Last Modified Date: April 17, 2003