Confounders

 

In Observational studies we always have to deal with confounders. A confounder is a difference in your study among the participants other than the factor you are trying to compare that ends up making your results less sensible.

For example, your customers from a certain location may possess unique characteristics compared with the rest of your customers.

These smaller subgroups exhibit similar shopping behaviors. In other words, they don’t have the internal variation that might skew your results and give you the wrong ideas.

Hence it’s a good idea to divide your groups into smaller subgroups, to get your confounders under control.

Avoiding confounders is all about splitting your customers into groups correctly. You will need to skim through your existing survey data and try to find the groups which are internally homogenous.

For example, ask yourselves questions like below:

How does your perceived product value compare among all your geography groups of stores/customers?

Was your company right about all their customers being happy with the value of their product?

https://youtu.be/e8Rdm2tbgtc