Inference for Two Categorical Variables

Let's carry the analysis a step further. In Chapter 8 we looked at the likelihood of ignition in connection with a major disruption, and we estimated that approximately 81% of incidents involved ignition. Is the risk of ignition somehow related to the type of disruption? In other words, are IGNITE and LRTYPE_TEXT independent? You might remember that we discussed independence back in Chapter 5 and used the conditional probabilities from a contingency table to make decisions about whether two events were independent. In Chapter 5 the subject was the behavior of dolphins and we considered two events at a time. With the current example, we'll ask a broader question: are the variables independent of one another? ...

Get Practical Data Analysis with JMP® now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.