Revision To Seasonal Adjustment Factors

Beginning with the Unemployment Insurance (UI) Weekly Claims News Release issued Thursday, April 6, 2023, the methodology used to seasonally adjust the national initial claims and continued claims reflects a change in the estimation of the models. Seasonal adjustment factors can be either multiplicative or additive. A multiplicative seasonal effect is assumed to be proportional to the level of the series. A large increase in the level of the series will be accompanied by a proportionally large seasonal effect. In contrast, an additive seasonal effect is assumed to be unaffected by the level of the series. In times of relative economic stability, a multiplicative adjustment is generally preferred over an additive adjustment. However, in the presence of a large level shift in a time series, multiplicative seasonal adjustment factors can result in systematic over- or under-adjustment of the series. In such cases, additive seasonal adjustment factors are preferred since they tend to track seasonal fluctuations more accurately in the series and lead to smaller revisions. Prior to the pandemic, the unemployment insurance claims series used multiplicative models to seasonally adjust the claims. Starting with March 2020, Bureau of Labor Statistics (BLS) staff, who provide the seasonal adjustment factors, specified both of the UI claims series as additive. After the large effects of the pandemic on the UI series lessened, the seasonal adjustment models were once again specified as multiplicative models. Statistical tests show that the UI series should, in normal times, be estimated using multiplicative adjustments. While the pandemic period remains within the five-year revision period, the UI series will be treated as a hybrid adjustment. The most volatile economic period of the pandemic, including the period running from March 2020 to June 2021, was not revised and will continue to be based on additive adjustments. Before and after these periods, both series are adjusted using multiplicative adjustments. For consistency, the published seasonal factors are presented as multiplicative with additive factors converted to implicit multiplicative factors and will not be subject to revision. Now that the pandemic impacts on the on the UI claims series are clearer, modifications have been made to the outlier sets in the seasonal adjustment models for both of the claims series. This led to larger than usual revisions during many weeks over the last 5 years, however, these changes should provide a more accurate picture of claims levels and patterns for both initial and continued claims. 

Original source can be found here