Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)



The 'Average Man'

The average man is a hypothetical person, supposed to typify the majority of a population or workforce. This description implicitly excludes portions of the population that are very different from the majority, such as the extremely rich or the Managing Director.

The idea of the average man usually surfaces when 'average' wages are discussed. All too often most people earn relatively little, but a very small number have a very large income indeed. If you simply work out the average income, the amount you calculate is very heavily influenced by one or two people. It certainly has very little to do with the position of the 'average man', as most people see him.

One way of dealing with this problem is to simply leave out these 'atypical' values. However, this causes all sorts of problems, partly because it highlights still further the difference between the mass of ordinary people and a privileged few.

Therefore, what is required is some way of including these values without them unduly distorting the overall picture. In practice, the way this is done is by some form of 'weighting' or 'transformation' - such as using geometric means.

When analyzing data, you often need to use similar methods, though usually for rather different reasons. For example:

  1. You may have few observations of variable data - so leaving out precious data is hard to justify.
  2. Or your overall distribution may be skewed - therefore you need to change the overall emphasis, rather than just a few points.
  3. You may have varying confidence in your data - some may summarize very few observations, or be from an unreliable source.

Which method is best depends upon your data, and the analysis you wish to perform.