Smoothed Seasonally Adjusted Metropolitan Area (SSA-MA) Estimates: Questions and Answers

  1. Why is BLS producing smoothed seasonally adjusted metropolitan area estimates?

    The development of seasonally adjusted estimates for metropolitan areas has been a long-standing goal of the Local Area Unemployment Statistics (LAUS) program. The production of smoothed seasonally adjusted metropolitan area (SSA-MA) estimates meets that goal and will allow for comparison of statewide and substate estimates within States. It will assist users in analyzing monthly trends in labor force estimates among metropolitan areas. It is also consistent with the practice of the Current Employment Statistics program, which produces seasonally adjusted estimates for nearly all metropolitan areas.

  2. What are smoothed seasonally adjusted (SSA) estimates?

    SSA estimates are seasonally adjusted estimates that incorporate a long-run trend smoothing procedure. This results in estimates that are less volatile than those produced using only seasonal adjustment estimation methodology.

  3. Did BLS previously produce smoothed seasonally adjusted estimates for some metropolitan areas?

    Yes. BLS previously produced and published monthly smoothed seasonally adjusted estimates for the following six metropolitan areas and metropolitan divisions as part of the LAUS time-series model estimation process:

    • Cleveland-Elyria-Mentor metropolitan area
    • Detroit-Warren-Livonia metropolitan area
    • Chicago-Joliet-Naperville metropolitan division
    • Los Angeles-Long Beach-Glendale metropolitan division
    • Miami-Miami Beach-Kendall metropolitan division
    • Seattle-Bellevue-Everett metropolitan division
  4. What methodology is BLS utilizing to seasonally adjust the metropolitan areas?

    BLS is using two methods to seasonally adjust the metropolitan areas estimates of employment and unemployment. The first is a model-based approach, Signal Extraction in ARIMA (Auto Regressive Integrated Moving Average) Time Series (SEATS), and the second is the non-model-based X-11, including X-11 ARIMA and X-12 ARIMA. The latter has been the standard BLS approach to seasonal adjustment since the 1970s. Both methods are accepted statistical procedures for seasonal adjustment. The approach that yielded the best results--SEATS or X-11--was used for each employment and unemployment time series.

  5. What are the differences between SEATS and X-11 seasonal adjustment methods?

    X-11 and SEATS have strong similarities. The ARIMA model of the observed series is the starting point for both. They both also use the same basic estimator, which is a weighted moving average of series that produces seasonally adjusted output. Their methods differ in the derivation of their moving average weights.

    X-11 is empirically based. It directly selects moving averages from a pre-specified set. The weights are not designed for any specific series, but fit a wide variety of series. SEATS derives a moving average from the ARIMA model of the series. The moving averages are tailored to the specific modeled properties of the series.

    The SEATS methodology is flexible in that it can adjust some series that X-11 finds too variable. It also facilitates analysis with a variety of error measures produced within the system. An advantage of X-11 is that it does not require a model to seasonally adjust a series. Also, it may prove useful in adjusting some complex series where SEATS produces highly variable seasonal factors.

  6. What methodology is used to smooth the seasonally adjusted metropolitan area estimates?

    BLS is using the Henderson 13 smoothing algorithm to smooth the metropolitan area estimates. This is the same methodology employed for the State and substate modeled estimates.

  7. How many metropolitan areas are being seasonally adjusted?

    We produce seasonally adjusted estimates for all 414 metropolitan series: 380 metropolitan areas (372 in the United States and 8 in Puerto Rico) and 34 metropolitan divisions. This count includes the 2 metropolitan areas and 4 metropolitan divisions that are seasonally adjusted through the LAUS models. (For the Commonwealth of Puerto Rico and its metropolitan areas, the Henderson 13 filter smoothing step is omitted.)

  8. How will BLS publish the SSA-MA data?

    Smoothed seasonally adjusted metropolitan area and metropolitan division labor force estimates will be posted on the BLS web site at

  9. What data will be published?

    We will produce smoothed seasonally adjusted estimates of civilian labor force, employment, unemployment, and the unemployment rate for the period January 2000 to the latest month.

  10. When will the data be issued?

    The tables will be loaded to the web site each month at approximately 3:00 p.m. ET on the day of the publication of the Metropolitan Area Employment and Unemployment news release. The release dates for all of 2011 can be found at

  11. Who can users contact for more information on the SSA-MA project?

    Users should contact Walter Sylva, Branch Chief, LAUS Research and Methods, at, or by mail at Bureau of Labor Statistics, 2 Massachusetts Avenue, NE, Suite 4675, Washington, DC 20212, with any questions.


Last Modified Date: June 29, 2011