// BLOG
Athens Banner Herald Article
July 24, 2011
The ABH has given us some love in their Sunday addition of the paper. Check it out online or go pick up an “analogue” copy from the newsstand! Thanks again to everyone for their encouragement and support. Please remember that we are still taking donations for the Children’s Miracle Network at
View the article at:
http://www.onlineathens.com/stories/072411/spo_861435685.shtml
Thanks
Robert
Inside Job
March 17, 2011
Here is a nicely done documentary on the underpinnings of the financial crisis. I have to give the short disclaimer that it is a bit biased….but it does provide well thought out analysis of the current power structure on wall street. Oh,…..and it is narrated by the dreamy Matt Damon. Here is the link:
http://topdocumentaryfilms.com/inside-job/
Online Herd Instincts
February 28, 2011
A recent article in the Economist points out our susceptibility to herding behavior. By design we are a social species and our ancient tendencies translate to our modern web and digital preferences. A study that analyzed Facebook app downloading data shows that most apps are only downloaded by a small number of users, but there are some apps that catch the attention of the herd and are catapulted to super stardom. This phenomenon highlights our hardwired herding tendencies and also shows that most social and human events are not normally distributed. Most social interactions are characterized by extreme skewness and kurtosis…..and we are often left with one BIG winner and many losers.
Here is the link to the full article and some quoted text below: http://www.economist.com/node/21011810
As the pair report in the latest Proceedings of the National Academy of Sciences, they pored over (anonymous) data of the entire Facebook population in July and August 2007 (around 50m at the time), and at all but a few of the 2720 apps available for download in the same period. This amounted to a total of some 104m app installations. At that time, a Facebook user’s apps were all visible to friends, who were also notified when any new app was downloaded (a practice Facebook has since abandoned). This, along with a display of the total number of installations of each app, were the only ways apps were plugged, permitting the researchers to control for the effects of external advertising. Any effects observed would thus be wholly attributable to social influence, not canny ad men.
Dr Reed-Tsochas and Dr Onnela duly discovered that the social networkers’ herd mentality was intact, with popular apps doing best, and the trendiest reaching stratospheric levels. A typical app was installed around 1,000 times, but the highest-ranked notched up an astonishing 12m users. What did come as something of a surprise, though, was that our inner lemming only kicked in once the app had breached a clear threshold rate of about 55 installations a day. Any fewer than that and users seemed oblivious to their friends’ preferences. Interestingly, after some serious number crunching, the researchers found that this cannot be put down purely to the network effect, ie, the idea that adopting a certain innovation only makes sense if enough other people have done so. Indeed, this effect appeared less pronounced than might have been expected.
Moreover, the data suggest that the sudden spike in installations doesn’t come about simply because a discovered threshold has been passed. This means the observed threshold rate is unlike an infectious disease’s basic reproduction number. (This is what epidemiologists call the average number of secondary cases caused by a typical infected individual in a population lacking immunity, with no efforts to control the outbreak.) In other words, it would be inaccurate to speak of an epidemic of popularity. Rather, Dr Reed-Tsochas and Dr Onnela suggest that two discrete behavioural patterns emerged. Users appeared to treat any app with more than 55 daily installations differently to those with fewer downloads. Under 55 daily installations, friend behaviour was an instrumental part of the decision to install. Over 55 daily installations, and friend behaviour didn’t matter one jot. Virtual lemmings are, it seems, discriminating in ways we still don’t quite comprehend. As is, no doubt, the offline troop.
This American Life
February 1, 2011
Statistics for Cyclists
December 28, 2010
Here is a simple statistics problem that could cause a cyclist a lot of grief. Lets say that we know that 1 out of 1000 cyclists are doping with Chemical X (for you cartoon fans out there…this is a Power Puff Girls reference). Now, lets assume that we have a test to detect Chemical X that is 95% accurate. This means that it will produce 5% false positives (meaning that a tested cyclist that has not taken the drug will get a positive test result 5% of the time on average).
So now the question is….if we randomly test our sample of cyclists and one has a positive test results what is the probability that he actually took the drug?? Most will answer that there is a 95% chance that he is a cheater….because the test is 95% accurate…this seems reasonable but is completely wrong!
The correct answer is that we must take the ratio of know cheaters to the true and false positive test results. ie .. there will be 1 true cheater for every 51 positive test results. Therefore the true probability is 1/51……about 2% that he is a cheater give one positive test.
This is a scary thought for a young cyclist that is constantly being tested for Chemical X because even the insinuation that he is a doper can end his career. A positive test will destroy his character….but there is only a 2% chance that he is the real cheater!!!
