Monday, June 2, 2014

SUPER ERROR: Stone & McCarthy Economist Finds Market-Roiling ISM Error

An economist at Stone & McCarthy Research Associates spotted an error in a closely followed index on U.S. manufacturing activity that led to the report being corrected -- twice.

Bloomberg has the details:
The Institute for Supply Management corrected its May index more than two hours after its initial 10 a.m. release, saying a wrong seasonal adjustment produced an inaccurate drop. Kenneth Kim, an economist at Stone & McCarthy in Princeton, New Jersey, had already crunched the numbers and couldn’t square the raw data with the ISM’s figures.

“I knew there was a discrepancy that showed something was not right,” Kim said in an interview. On a hunch, he applied the April seasonal adjustment to the raw data for May and came up with the number initially released by ISM.

“It showed that’s where the source of the error was,” Kim said. “Once that linked up, I felt very comfortable that was the error that had occurred.”

The ISM first reported that its factory index dropped to 53.2 in May from 54.9 the prior month, signaling a slower pace of expansion that surprised economists and pushed stocks down. Later, the Tempe, Arizona-based purchasing managers group issued a correction, saying its gauge rose to 56, sending stocks up. It then issued a second correction, saying the index was 55.4, the number Kim had originally calculated.

“Our research team is analyzing our internal processes to ensure that this doesn’t happen again,” ISM factory survey chairman Bradley Holcomb said in a statement.

It should be noted that this was, in many ways, a very easy error to spot. Who knows what goes on deep in the raw data that the government crunches. I have said many times that if the government wanted to massage a number, they wouldn't do it in a manner that could be easily detected (even by most employees), it would be deep in the number crunching phase, where few tread.-RW.

No comments:

Post a Comment