who ]
first ] random ] last ] calendar ]
links ]

 «  2004/02/19  »   1152

logic rant 

I was listening to the radio on my drive to work yesterday, which is something I rarely do anymore. I just can't stand CBC's Anna Maria Tremonte. But I made an exception because I was interested in the topic: doctors reporting adverse drug reactions, a discussion stemming from people buying internet drugs in Canada. Anyway, they had this woman on who felt Health Canada should've warned her about the possible reaction she'd have with human-based insulin (as opposed to animal-based). This woman had looked at some raw numbers which stated that there were something like 7000 cases of adverse reactions to human insulin in 2003 versus 600 with animal insulin (I'm paraphrasing heavily here -- the point is the magnitude of difference in the numbers).

And from these numbers alone the woman was ranting and raving about how obvious it was that human insulin should come with a warning, how irresponsible Health Canada is, etc etc. And that kind of mentality just drives me nuts.

Firstly, you cannot compare two bald numbers like that and say A is worse than B. If 7 million people took the human insulin, and 0.6 million took the animal insulin, that's comparing 0.1% versus 0.1%. And with any study, you can't go by the bottom numbers alone -- perhaps there was a bad batch of human insulin that year, resulting in more incidents. Maybe the human insulin was given to people who were more prone to adverse reactions to any insulin. Maybe the people who took human insulin got sick from animal insulin, started to take the human one, continued to become sick anyway and reported the human insulin as bad. The point is, there are just way way too many factors for anyone to take a glance at some summary numbers and say human insulin is definitely worse than animal insulin.

The sad thing is, this sort of mentality pervades us, everywhere and everyone. Take sport statistics for example -- I would say that 90% of sport statistics are useless. Absolute garbage. They may be correct, but they're misleading. One should always remember that the games define the statistics, NOT the other way around, as so many newscasters would like you to believe. If a team is on a 10 game win streak, does it mean that the team is good? Or that it has managed to play 10 really poor teams? Or that it's been especially lucky? You can't tell from that little factoid of a 10 game win streak -- you have to review each of those ten games and determine the reason they were won. And so, based on what you've found, then maybe you can make an accurate prediction on whether they'll win their eleventh. It would be even more accurate if you could research the status of the opposing team. But you can't predict the result based on, "Well, they've won 10 in a row, chances are they'll win the 11th." I have to shout NO!!!! whenever I hear that kind of illogic.

It's everywhere, and it's harmful. Using ticket sales to determine how "good" a movie is, or record sales, or car sales, or whatever! Do the research, see WHY the numbers are what they are. I know most of my readers aren't prone to such gross wash-over statements, but I still feel I need to rant about it. How has such.. simplistic thinking permeated into society? I implore you to stamp out such wicked ignorance from feigning itself as being thoughtful. Because it is not, and to believe it is is to fool oneself, or worse, fool others. Over and over again, without meaningful results.

[Comment on the above]

theMediaDork (hp)
A study was done and showed that 98% of statistics are wrong...

...think about it.

Growl
Something about teaching statistics I found: Ubi dubium, ibi libertas

Also, here's a book I read years ago: Innumeracy.

Lastly, do you really think people act on the basis of data, ever, whether misleading or not? They resist it with their every last ounce of strength *Picard voice* and just go with their prejudices, I think.

Hwan (hp)

I honestly believe that many people are prone to making judgments based on unreasonable statistical grounds -- the lady on CBC was certainly one shining example. Really, I cannot count the number of occurances I encounter a day. It's in the media AND the government, and even if we, the citizens, resist the idea of being nothing more than numbers, I think that the constant barrage of number-play from these two extremely powerful and influential sources has managed to convince many of the "If A then obviously B" doctrine.

Those are good links. I think I'll try to pick up a copy of Innumeracy.

Recent comments

2010/08/03 Hwan I won't say that all is well (for I don't believe it to be so), but I am better. Thanks to all for asking!
2010/07/20 QYV Expected range for Creatinine for guys is 60 - 110 umol/L
2010/07/20 llamariffic Hmm, macrocytosis here as well, but to be honest I've had it since before I truly embarked on drinking as a proper hobby. Similarly, stopped drinking entirely, and it didn't go away. Just one of those things, I think.
2010/07/19 girl ack!! It's weird to think that I am now a parental unit. It was nice to see you hwan!
2010/05/21 Hwan I recall trying earplugs well back in my undergrad years, to mixed results. My sleep was troubled by feelings of claustrophobia. I also have a, perhaps unfounded, fear of not hearing the essential alarm in the mornings. However, I may give these another go, thanks.
2010/05/21 llamatron Have you tried sleeping with earplugs? My flat faces out onto a main road, so I've started using the standard foam plugs. It took a few nights to get used to them, but they make a big difference.
2010/05/21 girl The original swedish title: "Men who hate women". I'm not sure if it's the fault of the translation, but I never liked the reporter dude.
2001/03/07 Hwan Damn.. it seems Unweb has since died. http://www.gamegrene.com/node/183
2001/03/07 TY SHARDEL YOU CAN TRADE WITH THE UNIVERSE AND ENABLE SOCIAL NEEDS, OR PERHAPS POST WISH LISTS, HUG THE GLOBE LIKE A BIG OCTOPUS... TY
2010/03/24 Hwan I am amused by the John Irving comparison. http://en.wikipedia.org/wiki/John_Irving#Recurring_themes

[X]

Google