BLS Establishment Estimates Revised to Incorporate March 1998 Benchmarks - United States Bureau of Labor Statistics - Statistical Data Included

Employment and Earnings, June, 1999 by Sheila McConnell

Both the universe counts and the establishment survey estimates are subject to nonsampling errors common to all surveys--coverage, response, and processing errors. The error structures for both the CES monthly survey and the UI universe are complex. Still, the two programs generally produce consistent total employment figures, each validating the other. Over the prior decade, annual benchmark revisions at the total nonfarm level have averaged 0.3 percent, with an absolute range from less than 0.05 percent to 0.7 percent.

Effect of benchmark revisions on other series

The routine benchmarking process also results in revisions in the series on women workers and production or nonsupervisory workers. There are no benchmark employment levels for these series; they are revised by preserving ratios of employment for the particular series to all employees prior to benchmarking, and then applying these ratios to the revised ail-employee figures. These figures are calculated at the basic cell level and then aggregated to produce the summary estimates.

Average weekly hours and average hourly earnings are not benchmarked; they are estimated solely from reports supplied by survey respondents at the basic estimating cell level. The broader industry groups of the hours and earnings series, however, require a weighting mechanism to yield meaningful averages. The production or nonsupervisory worker employment estimates for the basic cells are used as weights for the hours and earnings estimates for broader industry groupings. Adjustments of the all-employee estimates to new benchmarks may alter the weights, which, in turn, may change the estimates for hours and earnings of production or nonsupervisory workers at higher levels of aggregation.

Generally, new employment benchmarks have little effect on hours and earnings estimates for major groupings. To influence the hours and earnings estimates of a broader group, employment revisions have to be relatively large and must affect industries that have substantially different hours or earnings averages than other industries in their group. Occasionally, corrections of errors in the reported payroll data for individual establishments may also change the averages of selected industries. Table 4 gives detailed information on revisions to specific hours and earnings series resulting from the March 1998 benchmark. At the total private level, average hourly earnings and average weekly hours were unchanged.

Table 4. Effect of March 1998 benchmark revisions on hours and earnings estimates, selected industries