Content area
Full Text
Measuring economic growth is complicated by seasonality, the regular fl uctuation in economic activity that depends on the season of the year. The Bureau of Economic Analysis uses statistical techniques to remove seasonality from its estimates of GDP, and, in 2015, it took steps to improve the seasonal adjustment of data back to 2012. I show that residual seasonality in GDP growth remains even after these adjustments, has been a longer-term phenomenon, and is particularly noticeable in the 1990s. The size of this residual seasonality is economically meaningful and has the ability to change the interpretation of recent economic activity.
(ProQuest: ... denotes formulae omitted.)
Every quarter, the Bureau of Economic Analysis (BEA) releases estimates of gross domestic product (GDP), an indicator that is generally taken to be the broadest measure of the country's economic activity. Because of its wide applicability, both policymakers and business economists closely follow the BEA's estimates of GDP growth in order to monitor the pace of economic growth and watch for potential recessions.
However, tracking the health of the economy with GDP is complicated by seasonality, the regular fluctuation in economic activity that depends on the season of the year. This seasonal fluctuation partly depends on natural cycles. For example, new houses are most commonly started in the spring and built over the summer when the weather is the most accommodating. Seasonality also results from social customs. For example, end-of-year holidays, such as christmas, generate increased gift-giving and consumer spending in the fourth quarter of the year.
Seasonality is large and makes assessing the state of the business cycle difficult.1 Thus, the BEA uses statistical techniques to remove seasonality from its estimates of GDP, and these estimates are commonly taken as reliable indicators of the health of the economy that are free of seasonality. However, economists have recently begun to ask if there is residual or leftover seasonality in GDP, and they have not reached an agreement. Rudebusch, Wilson, and Mahedy (2015) and Stark (2015) argue that residual seasonality does exist. However, Groen and Russo (2015) and Gilbert, Morin, Paciorek, and Sahm (2015) disagree.
In this Commentary, I revisit the question of whether the BEA's estimates of GDP from 1985 to 2015 contain residual seasonality.2 I do so...