Understanding the Difference Between Predictions and Forecasts

I am an admitted stats geek. Every since I turned over my first baseball card to look at the past year’s stats of my favorite baseball player, I have had a fascination with statistics. When I majored in psychology in college, I found that stats played a major role in that field as well.

That is why when my son presented me with Nate Silver’s book “The Signal and the Noise: Why So Many Predictions Fail — But Some Don’t”, I was intrigued. I knew he was the hot ticket as regards political predictions having called not only the presidential election correctly but 49 out of the 50 key races in each state. Republicans pooh poohed him since many of his predictions went against the Republican grain but if you read his book, his political leanings (left as they may be) have absolutely nothing to do with his work. On the contrary, if you approach statistics as scientifically as Mr. Silver does, you are going to account for any prejudice in your findings.

The book takes each chapter as a separate case study. One addresses how the financial melt down of 2008 could have been easily avoided. The signs for the impending problem were all there but the key players were making so much money, nobody wanted the merry-go-round to stop turning. Another chapter looks at baseball, a perfect laboratory for statistics since every pitch and at bat has been documented for over 100 years.

Mr. Silver spent 4 years researching and writing the book and, as such, the opinions are not just his but those of experts in a variety of fields who help create the conclusions he puts forward. If you are looking for a magic bullet that will determine every political race, when to buy or sell stocks, who will win the world series and how to beat Las Vegas at their game, this is not the book for you. Rather than provide a single answer, Mr. Silver points out that well researched statistical predictions do not provide one answer. They provide a series of potential outcomes and express them by a percentage of probability.

For me, this book was a rich desert (and I like deserts). As I like reading about politics, business and financial matters, baseball and gambling, this book was a home run for me. Every chapter was an adventure and gave me new insight into the field.

Because of the way the book is structured, if there is a chapter that is not of interest to you, can can skip it and find out how weather forecasters have made some of the greatest strides in the past 20 years of all people in the prediction business but the ability to predict earthquakes is not much better than it was 50 years ago.

I happen to be interested in all of the areas in which the book explores. Give it a read. It is sure to open up your mind about how you look at your business and how you make your investments, if not anything else.

But lest I forget, here is how Mr. Silver defines the difference between a Prediction and a Forecast.

“1. A prediction is a definitive and specific statement about when and where an earthquake will strike: for instance a major earthquake will hit Kyoto, Japan on June 28.

2. A forecast is a prohabilistic statement, usually over a longer time scale: there is a 60 percent chance of an earthquake in Southern California over the next thirty years.”

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s