Statistical Variation in New Home Sales Reports

I just couldn’t pass up this up – I was reading the New Residential Sales stats report by the Department of Housing and Urban Development that was issued this afternoon. Apparently, sales of new one-family houses in October are up 1.7% over September’s sales numbers. These stats are so loaded with meaning that entire swings in the market take place at their utterance. This is the number I hear repeated on NPR, read aloud by talking heads and discussed by bloggers; the only thing is, you never hear about the statistical variation in the report. To see what I mean, read the official excerpt from today’s report below:

“Sales of new one-family houses in October 2007 were at a seasonally adjusted annual rate of 728,000, according to estimates released jointly today by the U.S. Census Bureau and the Department of Housing and Urban Development.
This is 1.7 percent (±11.0%)* above the revised September rate of 716,000 and is 23.5 percent (±10.3%) below the October 2006 estimate of 952,000.
The median sales price of new houses sold in October 2007 was $217,800; the average sales price was $305,800. The seasonally adjusted estimate of new houses for sale at the end of October was 516,000. This represents a supply of 8.5 months at the current sales rate.”

A statistical variation of “±11.0%”?!?
That means the “real” number could either be 12.7% more sales or -9.3% sales over the prior month’s numbers? This is the quality of data that sets real estate and stock markets on fire or on ice? I think a much more honest report would say “We don’t have the foggiest idea what the numbers are; in fact, your guess is probably as good as mine!”
I couldn’t help but dig in a little deeper to see what that asterisk meant hanging off of that “±11.0%” figure in the report. At the bottom of the report, the “Explanatory Notes” say that “Whenever a statement such as ‘2.5 percent (±3.2%) above’ appears in the text, this indicates the range (-0.7 to +5.7 percent) in which the actual percent change is likely to have occurred.” At least they acknowledge the possibility of wild swings in the output.
All of this was simply to say – take your statistics with a grain of salt and double-check the sources and their publishers’ intentions. There is no such thing as unbiased data; dig in a little deeper and try and put the information into a context that makes sense for you. For example, I think it is foolish to simply assume the national new home sales numbers automatically reflect on Orange County’s numbers. Real estate is and will always be beholden to local market trends & issues, despite best-efforts to wrap them up into tasty sound bites that fit neatly between commercials.
Here’s a link to the original report:
There is meatier statistical-data collection methodology described on the Statistics Collection Methods section on the site here –

Related Posts Plugin for WordPress, Blogger...



Submit a comment