Don’t be a Turkey

11 years ago

[This article was first published on R-Chart, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)

Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

‘Indeed, I am moving on: my new project is about methods on how to domesticate the unknown, exploit randomness, figure out how to live in a world we don’t understand very well. While most human thought (particularly since the enlightenment) has focused us on how to turn knowledge into decisions, my new mission is to build methods to turn lack of information, lack of understanding, and lack of “knowledge” into decisions—how, as we will see, not to be a “turkey”.’

– Nassim Nicholas Taleb

With thanksgiving on the way, an economic lesson provided by a turkey’s statistical department seems appropriate. Our turkey – let’s call him auRthur – like most turkeys has a statistical department at his disposal. His department is in fact tracking an index – the Turkey Welfare Index which is a reflection of how much the human race cares about auRthur. Notice the relatively positive trend… until < whack> Thanksgiving Day…

Evidently, our auRthur’s statistical department utilized a model that had some flaws – “past performance is not necessarily a predictor of future returns”. This is because the harvesting of the turkey is a “rare event.” Rare (unprecedented) events are difficult to predict. The story is not terribly amusing to turkeys to begin with – but becomes less amusing to humans when understood as a metaphor of the financial meltdown and statistical modeling in use by banking institutions. Essentially, banking institutions assumed a huge amount of risk because a catastrophic meltdown was simply outside the realm of consideration. It was not represented in most of the models in use.

A great and vivid illustration. See Nassim Nicholas Taleb’s essay where this chart and illustration originally appeared at edge.org. This article discusses the limits of statistical thinking and is a good springboard to other writings by Taleb – who was a practitioner of risk as he ran a hedge fund for a number of years and saw many of the practices in the financial industry up close and personal.

The chart above was created using R and ggplot2. The data frame named DF was populated with data related to the Turkey Welfare Index.

> DF
   TWI Day color
1 14 1 black
2 15 2 black
3 16 3 black
4 17 4 black
5 18 5 black
6 19 6 black
7 20 7 black
8 -100 8 red

UPADTE: This can be entered in a few different ways. One is through a grid (which requires that you specify the Day as a factor).

  DF=edit(data.frame())
  DF$Day=factor(DF$Day)

Plotted using ggplot2:

library(ggplot2)

ggplot(data=DF, aes(x=Day, y=TWI, fill=color)) +
  geom_bar() +
  scale_fill_manual(value= c(“black”, “red”)) +
  theme_bw() + scale_x_discrete(breaks = NA) +
  opts(legend.position=’none’, axis.title.x=theme_blank(),
   axis.title.y=theme_blank(),
   title=’Turkey Welfare Index’)

This included a couple of somewhat unusual settings to shut off labels and axes that results in the simple “plain” appearance you see above.

So – Happy Thanksgiving – understand statistics and don’t be a turkey…

To leave a comment for the author, please follow the link and comment on their blog: R-Chart.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.

Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.