Linear regression – an introduction

Introduction: the price of wine

There are differences in price and quality of wine from year to year that are sometimes very significant: wines are tasting better when they are older. So,  there is an incentive to store young wines until they are mature.
Wine experts taste the wine and then predict which ones will be the best later.
But it is hard to determine the quality of the wine when it is so young just by tasting it, since the taste will change significantly by the time it will be consumed .

We have seen that on March 4, 1990, the  Princeton Professor of Economics Orley Ashenfelter announced that he can predict the quality of Bordeaux wine without tasting a single drop but just using a mathematical model.

Ashenfelter used a method called linear regression.

The method predicts an outcome variable – the wine price – using one or more independent variables – such as the wine age or the weather.

The initial reaction was of skepticism.
Robert Parker, the world’s most influential wine expert said : “Ashenfelter is an absolute total sham. He is like a movie critic who never goes to see the movie but tells you how good it is based on the actors and the director” but the method proved its validity very soon.

Let’s see how Ashenfelter was able to predict reliably the wine price. Continue reading “Linear regression – an introduction”