Bert Gunter wrote:> Folks:
>
> Thought that many on this list might find this amusing, perhaps even a bit
> relevant. Hope it's OK:
>
> ************
> WASHINGTON - The government's estimate of the number of Americans
without
> health insurance fell by nearly 2 million Friday, but not because anyone
got
> health coverage.
>
> The Census Bureau
> <http://search.news.yahoo.com/search/news/?p=Census+Bureau> said it
has
> been overstating the number of people without health insurance since 1995.
> The bureau blamed the inflated numbers on a **12-year-old computer
> programming error**.[emphasis added -- BG]
> **************
>
> So what does "validated software" really mean? (Rhetorical
question -- no
> reply sought).
>
>
Details of what went wrong are at
http://www.census.gov/hhes/www/hlthins/usernote/usernote3-21rev.html
(executive summary: They imputed coverage for some people who were
actually covered by another household member's policy).
Looks like a mistake you can make in any programming language...
> Cheers to all,
>
> Bert Gunter
> Genentech Nonclinical Statistics
> South San Francisco, CA 94404
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>