Variable Trends in Economic Time Series

T he two most striking historical features of aggregate output are its sustained long run growth and its recurrent fluctuations around this growth path. Real per capita GNP, consumption and investment in the United States during the postwar era are plotted in Figure 1. Both growth and deviations from the growth trend-often referred to as "business cycles"-are apparent in each series. Over horizons of a few years, these shorter cyclical swings can be pronounced; for example, the 1953, 1957 and 1974 recessions are evident as substantial temporary declines in aggregate activity. These cyclical fluctuations are, however, dwarfed in magnitude by the secular expansion of output. But just as there are cyclical swings in output, so too are there variations in the growth trend: growth in GNP in the 1960s was much stronger than it was in the 1950s. Thus, changes in long run patterns of growth are an important feature of postwar aggregate economic activity. In this article we discuss the implications of changing trends in macroeconomic data from two perspectives. The first perspective is that of a macroeconomist reassessing the conventional dichotomy between growth and stabilization policies. As an empirical matter, does this dichotomy make sense for the postwar United States? What is the relative "importance" of changes in the trend and cyclical swings in explaining the quarterly movements in economic aggregates? We next adopt the perspective of an econometrician interpreting empirical evidence based on data that contain variable trends. The presence of variable trends in time series data can lead one to draw mistaken inferences using conventional econometric techniques. How can these techniques-or our interpretation of them-be modified to avoid these mistakes?