Via a Slashdot entry, I heard that NASA has released data from a survey they did from 2001 to 2004. They surveyed pilots, and apparently a lot of the responses did not reflect well on NASA, so the data was going to be destroyed. They changed their minds, and now the data has been posted for analysis - no one has really done a great job analyzing the data yet, so if anyone is interested... For the data, see the link here.
NASA data released for analysis
5 Comments
Leave a comment
Subscribe!
Andrew Gelman's Books
Research supported by the National Science Foundation
National Institutes of Health
Yahoo Research
Andrew,
Happy New Year first.
Second, one of the reason mentioned by some of the NASA people to, initially, not release the data was apparently linked to the fact that the survey was anonymous. Apparently if one incident had been mentioned by several respondents who were on the same flight, there was apparently no way of saying whether they talked about the same incident or if it was hearsay (friend of a friend who was on that flight). I think eventually the fear at NASA was that if you counted each report of incident as one, you could be thinking that indeed the public could have a safety concern when in fact it was a just counting issue coming from the anonymization process. I am not making a judgment but if indeed the survey was undertaken in this manner, some amount of care must be taken on the analysis. On the other hand, only NASA, an agency that still has a lot of public support, could have earned the trust of people in the survey yielding this data.
Igor.
You might want to read this article from npr before getting too excited - http://www.npr.org/templates/story/story.php?storyId=17728962&ft=1&f=1001
They haven't exactly made it easy - releasing the data in PDF format is about as far as you can get from the spirit of releasing the data as you can get, whilst still releasing the data.
I suppose they could have released it as a GIF, to make it harder.
Jeremy, Adobe Acrobat can save a file to text. I've checked it for this dataset, and it's interpretable.
It looks like at least one group is trying an analysis of this dataset:
http://www.avweb.com/eletter/archives/avflash/1030-full.html#196927
Igor.