Census Bureau Revisions to Retail Sales
Yesterday I posted my monthly update on Retail Sales. Those of us who routinely track this series know that the Advance Estimate, which is what we got yesterday, will be followed by a second estimate next month and a third estimate the month after. How big are those revisions? Big enough to warrant skepticism about the Advance Estimate?
Here is a visualization of the cumulative change from the first to third estimates from January 2007 through February 2013, the most recent month for which we have three data points.
As we see, revisions abound, and they move in either direction, although mostly downward during the last recession. For a better sense of the magnitude of the revisions, the next chart shows the percent change from the first (advance estimate) to third (second revision).
During this timeframe there were 33 upward revisions and 41 downward revisions. The absolute mean (average) revision was 0.38%, which breaks down as 0.30% for the upward adjustments and -0.44% for the downward adjustments.
Now, let's recall yesterday's 0.1% month-over-month improvement of April 2013 Advance Monthly Sales for Retail Trade and Food Services. The CB adds a parenthetical (±0.3%)* for that MoM advance estimate. The asterisk is expanded as follows:
|* The 90 percent confidence interval includes zero. The Census Bureau does not have sufficient statistical evidence to conclude that the actual change is different than zero. [PDF source]|
The message is clear: Don't take the initial retail sales data too seriously, which is the same message I've illustrated elsewhere for Bureau of Labor Statistic's jobs data.
Note: Actually there's yet more to the revisions than I've touched on in this discussion. We get annual revisions of the series as well. But for the purposes of this commentary, Im interested specifically in the month-over-month changes.