by Calculated Risk on 10/24/2008 06:29:00 PM

I've been using a two month method to predict PCE. This estimate suggests real PCE will decline by 2.4% in Q3.

Fed economists Riccardo DiCecio and Charles S. Gascon have used real time data to estimate PCE and check the reliability of this approach: Predicting Consumption: A Lesson in Real-Time Data (November 2008)

Whereas I used revised data for historical comparisons, the Fed economists only used data that was available for analysts at the time of the estimate (a much better test of the approach). The economists found that using the change in the second-month of each quarter (over the second-month of the previous quarter) was very reliable.

Click on graph for larger image in new window.

The chart plots the approximated (second-month) and actual growth rates of PCE since 1991 using real-time data: That is, the growth rates at each point on the chart are computed using only the data that would have been available to a researcher at the time of the estimate. The approximated measure for 2008:Q3 is –2.3 percent, suggesting the first decline in PCE since the fourth quarter of 1991.

Since PCE accounts for almost 71% of GDP, this also suggests the change in real GDP in Q3 might be negative. This depends on exports, changes in inventories and government spending (investment will certainly be negative in Q3).