Are you the next 'Outlier'?

I had the good fortune to read Outliers by Malcolm Gladwell over the holidays. (Amazon Link) Actually I listened to the audio book (Gladwell reads it). It is one of the few brooks I would recommend to everyone. It is a must-read for parents. One of the main ideas of the book (as I perceived it), is that success does not come in a vacuum. When you look at highly successful people (or outliers), they had numerous factors in place to allow them to succeed. They were at the perfect time and place. They had the perfect storm of previous experiences and opportunities to allow them to succeed.

Gladwell does an excellent job of providing numerous examples including the lives of Bill Gates, as well as, Bill Joy who founded Sun Micro-systems. Gladwell skillfully researched all the things in place for them to succeed. With both of these pioneers, their experience and skills put them in a unique place when the world changed and demanded personal computer programs (Gates) and programming for the internet (Joy).

This perspective immediately led me to think about the possibilities of becoming aware of the things that are in place for each of us. What experiences have we had or what unique skills sets have we amassed? How might we apply what we previously considered to be useless knowledge? What doors were or are being opened to us?

Or perhaps these questions can be applied to your child or someone you know.

The world is changing and becoming more specialized at such a rapid rate that there very well may be a rapidly growing need for your experience and skill set. So my suggestion is to read Outliers and think about the possibilities.

How might the changing world and its people need your (or your child’s or friend’s) unique blend of experience and skill?

1 comment (Add your own)

1. Sanjeev wrote:
Interesting post. I don't know that I would call the requirements "data clinnseag" (at least not the way I use the term .. see my blog at - it seems to me that since the "immediate goal is to isolate trend data for further analysis" it is more of a feature extraction problem.There are many ways of going about this. For the artificial data of Example 1, and if we take a post hoc view (that is we have seen all the data before we want to extract the trend information), then a regression with dummy variables to isolate the shock effect should suit the situation. Now, if you want an estimate of trend at every time period and you take the "sliding" viewpoint (that is, at any intant you know nothing about the future, and the shock comes as a complete shock to you) then a Bayesian approach might suit. Essentially you start with a prior for the mean and variance of the level and trend and update that as each new data point comes along. When an 'outlier' comes along, this increases (massively in this case) the instantaneous estimate variance of the variance of the level and the trend.. at that point you become very uncertain about future forecasts.You can find this sort of logic expounded in works by Harrison and West - google for BATS Bayesian Analysis of Time SeriesFor the second example, you might want to treat it the same way (Bayesian), or you might want (post hoc) to divide the series into epochs (pre and post period 16 are arguably different in kind; but post 16 looks like it could be one series with possibly increasing variance, and some persistence of shocks - it could possibly be modelled by an AR (autoregressive) approach. There is some commercial software called AutoBox that will do some of this sort of work automagically for you.Which approach you want to take depends on your objectives. Do you want a single number ("trend") for each time series? Or do you want to extract another time series called "forward estimate of underlying trend"? Or yet another possibility, a time series called "smoothed estimate of trend" (which involves looking forwards and backwards).

Wed, January 16, 2013 @ 1:42 PM

Add a New Comment


Comment Guidelines: No HTML is allowed. Off-topic or inappropriate comments will be edited or deleted. Thanks.