Bayes Rule and Cascades
https://www.linkedin.com/pulse/marketers-why-you-should-learn-bayes-rule-sarah/
In this article, Sarah Lewis describes the property of Bayes rule and its importance to Growth Marketing Hypothesis. She starts off by explaining the basic equation of P(A |B)=((P(A and B)xP(A))/P(B). This means the probability of event A given event B is equal to the probability of event A and B times the probability of event A divided by the probability of event B. However, it is made clear that this is not a casual relationship. Bayes rule is basically “the likelihood of a correlation despite a time gap”. It is helpful within situations of marketing as you can tell, given the event that the social media was changed, the engagement increased. This will allow for helping to make marketing decisions. It helps to weigh the evidence and see which event will create the largest impact.
In class, we expanded on bayes rules through the equation. P(A|B)= ((P(B|A)xP(A))/(P(B|A)xP(A)+(P(B|A’)xP(A’)). Which essentially means the probability of event A given B is the probability of B given A times the probability of A all divided by the probability of B given A times the probability of A plus the probability of B given complement A times the probability of A’. When there are more variables within the equation, you can get the probability of P(A|B) easier. Bayes rules can be used to infer on cascades and whether or not an information cascade is occuring. In a cascade, person 1 often follows their signal (unless explicitly otherwise), then person 2 takes the first person’s reaction into account and so on. The bottom line with bayes rule and cascades is that you are very likely to have a cascade if a lot of people are involved.