How do you work out what is important?

degrees-of-freedom.png

You usually have many options and lots to consider when approaching a problem.

Most people have experienced meetings where a number of people have opinions, approaches, suggestions and explanations for why you should do something in a particular way.

Quite often, you end up with a set of conclusions pulled together that include things that the group seems to like and things that important members of the group put their support behind.

That’s all good group work and “brainstorming” and does help with creativity and idea generation.

But how do you know which of those conclusions actually matter and are important?

A model from statistics called Degrees of freedom may help us here.

You need information and data in order to estimate a statistical parameter. The degrees of freedom in that estimate are the number of independent pieces of information needed to work it out.

In the picture above, to work out the result, you need four pieces of information: 1, 2, 3 and 4. The intermediate calculation a is from a calculation involving 2 and 3, and so is not independent.

This system has four degrees of freedom.

There are two things that this model helps us see.

The first is that information that does not affect the result should not go into the analytical process. You need to focus on the things that will “move the needle” and eliminate unrelated factors.

The second is that the larger the number of degrees of freedom, the more values the end result can take. In a physical example human upper arms have 7 degrees of freedom and can do a number of movements as a result. The hand has 23 degrees of freedom and can do much more.

The degrees of freedom concept can be generalised to help with general problem solving and business modelling.

You need to figure out which parameters can affect the result you want, and then isolate the parameters that are truly independent.

You then need to work out what a change in each parameter means for your result – you come up with scenarios. You can say things like if the first parameter changes by 10%, this is what it means for the result.

Then, if you want to get a little fancy, you vary all the parameters and come up with a range of results that might happen – modelling it stochastically. This lets you say things like I’m 80% confident that the result will be between X and Y.

In business, what this process lets you end up with are the parameters that matter to you – the ones that are important to monitor if you are going to achieve the necessary result.

These parameters are your Key Performance Indicators (KPIs). Keep an eye on them, make sure that they are within tolerance and doing what they should be doing, and you have a much better chance of getting the result you want.

The next thing then is to make sure that the result you are planning to get is the one you really want.

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