Has residual seasonality in GDP persisted after the latest BEA improvements? Cleveland Fed researchers reveal their findings
Despite improvements by the Bureau of Economic Analysis (BEA), Cleveland Fed researchers Victoria N. Consolvo and Kurt G. Lunsford find residual seasonality in GDP growth remains. On average, this residual seasonality makes GDP growth appear to be slower in the first quarter of the year and more rapid in the second quarter of the year than is actually the case.
Measuring economic growth is complicated by seasonality, the regular fluctuation in economic activity that depends on the season of the year. Because of its size, seasonality makes it difficult to assess the state of the business cycle. The BEA uses statistical techniques to remove seasonality from its estimates of GDP, but some research has indicated that seasonality remains. As a result, the BEA began a three-phase plan in 2015 to improve its seasonal-adjustment techniques, and in July 2018, it completed phase 3.
The Cleveland Fed researchers test if residual seasonality has persisted even after the BEA’s July 2018 benchmark revision. “Using the newly revised data for GDP and its components from 1985 to 2018, we find that first-quarter GDP growth has residual seasonality of annualized -0.6 percent and that second-quarter GDP growth has residual seasonality of annualized 0.5 percent,” say Consolvo and Lunsford.
Although the researchers’ estimates of residual seasonality are smaller in magnitude than those found in Lunsford’s earlier (2017) research, they say the continued presence of residual seasonality can complicate policymakers’ and business economists’ ability to monitor the pace of economic growth and watch for potential recessions in real time.
Another important result from Consolvo and Lunsford’s analysis is that despite the historical improvements by the BEA, the researchers find persistently low GDP growth for the first quarter of the year during the 1990s, suggesting the presence of residual seasonality over this time span that may remain unaddressed. “Given that historical GDP data are often incorporated into statistical models of forecasting and policy analysis, users of these models may want to consider seasonally adjusting GDP growth before producing forecasts or analyzing economic policy,” say the researchers.