By the way, one of my favorite misunderstandings of probability, which I've mentioned in my classes, came from the fall of Skylab in 1979 (younger TIPSters will have little idea what I'm talking about). I recall a NYC TV station asking people on the street about the likelihood that they'd be hit by a falling piece of Skylab. One gentleman, in complete seriousness, answered 50%. When the puzzled reporter asked him why, he responded (I'm paraphrasing), again, in complete earnestness, "Well, either it will hit me or it won't. So that's a 50% probability."
...Scott Scott O. Lilienfeld, Ph.D. Department of Psychology, Room 473 Emory University 36 Eagle Row, Atlanta, Georgia 30322 [email protected]; 404-727-1125 -----Original Message----- From: Jim Clark [mailto:[email protected]] Sent: Tuesday, September 20, 2011 11:00 AM To: Teaching in the Psychological Sciences (TIPS) Subject: Re: [tips] Statistics question: Death from the skies? Hi James M. Clark Professor of Psychology 204-786-9757 204-774-4134 Fax [email protected] >>> <[email protected]> 20-Sep-11 9:21:05 AM >>> NASA warns us of lurking risk of death from above (http://tinyurl.com/3jygt52 ), "within weeks". How great is the risk? NASA is quoted in a slightly garbled statement in _The Telegraph_ that there's a "1-in-3,200 chance a part a satellite part could hit someone". I've been pondering what meaning to attach to that statement. When I checked just now, the world population was 7,147,958,331 and counting. Dividng this figure by the stated chance of death by satellite gives a figure of over 2 million expected deaths. Now either this is absurd, or we're loooking at a major looming tragedy. The article, after all, does say that "senior space agency officials admitted they were "concerned" about the risk to billions of people." JC: The confusion is thinking that 1/3200 chance part hits someone means that each person has 1/3200 chance of being hit. Then the calculation "makes sense" mathematically. It is not clear how they came up with this probability. The article states that no one has ever been hit by a piece of space debris, despite such debris falling since space programs started. So that would appear to rule out an empirical determination (i.e., # hits / # opportunities). That would appear to leave some sort of theoretical calculation (i.e., # ways for hit to occur / # opportunities). Also, the probability applies just to this one incident of a large satellite expected to return to earth in the next few weeks. Not obvious how one computes a theoretical probability for this, unless you can estimate number of pieces re-entering earth and proportion of surface that would contain a person. Might make an interesting probability question?? Perhaps they mean that the risk only applies to those under the flight path of the satellite. But that's little comfort when we're told that the satellite "travels over a large band of Earth, avoiding only areas close to the poles". Alternatively, perhaps they only mean that for satellites in a situation similar to that which NASA warns us about, in only 1 out of 3,200 occasions of one falling down will it off even a single unfortunate individual out of the entire world's population. This is an almost unimaginably small risk for each of us. If that's the case, then all this NASA stuff is merely Chicken Little. Unless I hear otherwise, that's the one I'm going with. I'm coming out from under the bed now. JC: I don't know Stephen. This is probability for this one object. If there are many such objects, each with some probability of hitting a person, then the probability of being hit might increase markedly. p(hit by A) + p(hit by B) + ... , assuming independence. Take care Jim --- You are currently subscribed to tips as: [email protected]. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13509.d0999cebc8f4ed4eb54d5317367e9b2f&n=T&l=tips&o=12802 or send a blank email to leave-12802-13509.d0999cebc8f4ed4eb54d5317367e9...@fsulist.frostburg.edu ________________________________ This e-mail message (including any attachments) is for the sole use of the intended recipient(s) and may contain confidential and privileged information. If the reader of this message is not the intended recipient, you are hereby notified that any dissemination, distribution or copying of this message (including any attachments) is strictly prohibited. If you have received this message in error, please contact the sender by reply e-mail message and destroy all copies of the original message (including attachments). --- You are currently subscribed to tips as: [email protected]. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=12822 or send a blank email to leave-12822-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
