This is great!

Tpyos:

• Shortly after the sentence, "We could consider three hypothetical causal diagrams over only these two variables", one of the "Earthquake --> Recession" tables gives p(¬e) as 0.70 when it should be 0.71 (so it and 0.29 sum to one).

• After the sentence, "So since all three variables are correlated, can we distinguish between, say, these three causal models?", this diagram I think is meant to have "Recession" on top and "Burglar" on the bottom. (Vaniver also noticed this one.)

Edit:

• The paragraph that starts with "Sure! First, we marginalize over the 'exercise' variable to get the table for just weight and Internet use" needs to have s/normal-weight/overweight/ run on it. (And maybe have a sentence added saying that you're getting the rest of the following table by doing the same math on the other three sets of people grouped by weight and Internet usage.)