Each year, historical estimates from the Local Area Unemployment Statistics (LAUS) program are revised to reflect new population controls from the Census Bureau, updated input data, and reestimation. The data for model-based areas also incorporate new seasonal adjustment, and the unadjusted estimates are controlled to new census division and U.S. totals. Substate area data subsequently are revised to incorporate updated inputs, reestimation, and controlling to new statewide totals.
In conjunction with the current revision cycle, LAUS is undergoing a broad program redesign. The first phase of this redesign occurred on March 4, 2015, with the comprehensive replacement of data for census regions and divisions, the states and the District of Columbia, and a handful of large substate and balance-of-state areas based on a new generation of time-series models. The substate model-based areas are as follows: the Los Angeles-Long Beach-Glendale, CA Metropolitan Division; the Miami-Miami Beach-Kendall, FL Metropolitan Division; the Chicago-Naperville-Arlington Heights, IL Metropolitan Division; the Detroit-Warren-Dearborn, MI Metropolitan Statistical Area; New York city, NY; the Cleveland-Elyria, OH Metropolitan Statistical Area; and the Seattle-Bellevue-Everett, WA Metropolitan Division. The metropolitan areas and metropolitan divisions reflect the 2010 Census-based delineations issued by the Office of Management and Budget (OMB) in February 2013. Both not-seasonally-adjusted (NSA) and smoothed-seasonally-adjusted (SSA) and data were replaced back to their series beginnings in 1976, 1990, or 1994. Information on the new models is available in the Report on Revision to State and Area Time-Series Models.
Statewide data for Puerto Rico (both NSA and SSA) were revised on March 17 from January 2010 forward to reflect updated population controls. The NSA data for Puerto Rico are tabulated from a household survey similar to the Current Population Survey and generally are not subject to historical revision like the model-based estimates for states.
On March 17, substate estimates from January 1990 through December 2014 were controlled to the new NSA totals for model-based areas. At the same time, the federal statistical area geography was converted to the 2010 Census-based delineations that had been issued by OMB in February 2013. (More information on the new federal statistical areas is available at www.bls.gov/lau/lausmsa.htm.) The substate data from January 2010 through December 2014 were provisional as of March 17. Comprehensive revisions for substate areas from January 2010 forward subsequently were issued on April 21, reflecting methodological enhancements and the use of more timely estimation inputs from the Census Bureau's American Community Survey. (More information on the revisions to substate estimates is available at www.bls.gov/lau/lauschanges2015.htm.) Also on April 21, annual average estimates for substate areas in 2014 were issued.
On March 17, minor corrections were made to smoothed-seasonally-adjusted data for Puerto Rico (available directly at http://data.bls.gov/timeseries/LASST720000000000003) from January 1976 through December 2009. Changes to these data outside of the standard 5-year scope for re-adjustment had been issued on March 4. The corrections restore the historical data that had been overwritten inadvertently at that time.
On April 29, corrections were made to estimates for all substate areas in Idaho, Iowa, Georgia, Vermont, and Puerto Rico, as well as 17 interstate areas with parts in these states, for January 2015. The errors for Idaho, Iowa, Georgia, and Puerto Rico had resulted from incorrect employment estimation inputs, while the errors for Vermont had resulted from incorrect unemployment insurance claims estimation inputs. The corrections were mostly minor, with unemployment rates changing by more than 0.5 percentage point in only 17 small towns in Vermont, where single-digit changes in unemployment levels had relatively large impacts on the associated rate calculations.
On July 1, corrections were made to the following areas:
The corrections for Oregon areas were due to revisions to the total nonfarm payroll employment estimation inputs at the metropolitan area level. The largest relative correction for LAUS employment levels was 1.3 percent among Oregon areas, with unemployment rates changing by no more than 0.1 percentage point. The corrections for Washington areas (excluding the Seattle-Bellevue-Everett, WA Metropolitan Division and balance of state, which are model-based) were due to the incorporation of better unemployment insurance claims inputs. The relative changes to unemployment levels among Washington areas ranged from -18.0 percent to +13.0 percent, with 34 associated unemployment rate changes of 1.0 percentage point or more. For Puerto Rico areas, a processing error affecting the statewide inputs of agricultural and all other employment was corrected. For all but three small, heavily agricultural municipios, the relative corrections to LAUS employment levels were less than 5.0 percent, and the associated unemployment rate changes were less than 1.0 percentage point. The two interstate areas controlled by Oregon with parts in Washington—Portland-Vancouver-Salem, OR-WA Combined Statistical Area and Portland-Vancouver-Hillsboro, OR-WA Metropolitan Statistical Area—were affected from January 2012 through March 2015, beginning earlier and ending later than the corrections to the rest of Oregon's areas due to the changes in unemployment for their Washington parts. Estimates for all areas that were subject to change over these periods have been footnoted as corrected in the time series database.
Last Modified Date: July 2, 2015