When developing a model, it is important to consider what variable you choose. In doing so, the notion that the variable must be both observable and measureable are extremely important. Observable implies that we can see it. Measurable means that we have the ability to detect changes. Why are these important characteristics to consider? If a variable fails to have these properties, how would that influence analysis? Note: You may do this in the context of an example. If you want to go back to our previous QOW for examples that is fine. For example: How you both observe and measure something like work environment to understand how it affects costs? If you used workers self-reported information, would you expect it to be correct?