Those Pesky Details

A plunge in U.S. preschool obesity? Not so fast, experts say

But as obesity specialists take a closer look at the data, some are questioning the 43 percent claim, suggesting that it may be a statistical fluke and pointing out that similar studies find no such decrease in obesity among preschoolers.
In fact, based on the researchers' own data, the obesity rate may have even risen rather than declined.

...The 13.9 percent obesity rate among preschoolers reported for 2003-2004 had a large enough margin of error that the actual rate could range between 10.8 percent and 17.6 percent, the CDC authors acknowledged. The 8.4 percent rate in 2011-2012 reported could range from 5.9 percent and 11.6 percent.
the range for 2003-2004 overlaps with that of 2011-2012, Kabat said, "that's another way of saying there might have been no change" in preschoolers' obesity rate. Even an increase is a statistical possibility.

Yeah, I was skeptical of that conclusion.   Since no other groups showed any changes...