From 19a87123d06d6d372acffd35455c601d019fc9f1 Mon Sep 17 00:00:00 2001 From: Thomas Levine Date: Tue, 10 Sep 2013 18:24:37 -0700 Subject: [PATCH] non-fundamentelness of probabilities --- Chapter1_Introduction/Chapter1_Introduction.ipynb | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Chapter1_Introduction/Chapter1_Introduction.ipynb b/Chapter1_Introduction/Chapter1_Introduction.ipynb index 8b1e4578..4fe73cc5 100644 --- a/Chapter1_Introduction/Chapter1_Introduction.ipynb +++ b/Chapter1_Introduction/Chapter1_Introduction.ipynb @@ -239,6 +239,8 @@ "\n", "Notice that the plots are not always *peaked* at 0.5. There is no reason it should be: recall we assumed we did not have a prior opinion of what $p$ is. In fact, if we observe quite extreme data, say 8 flips and only 1 observed heads, our distribution would look very biased *away* from lumping around 0.5 (with no prior opinion, how confident would you feel betting on a fair coin after observing 8 tails and 1 head). As more data accumulates, we would see more and more probability being assigned at $p=0.5$, though never all of it.\n", "\n", + "**Potential point of confusion**: We're talking about probabilities in the above two paragraphs, but the use of a probability here isn't fundamental to the math. We're only talking about probability because we decided to estimate the probability that a coin lands heads. We could just as easily decide to estimate the average time it takes for the coin to land, in which case the x-axes on these graphs would be times (maybe in seconds) rather than probabilities.\n", + "\n", "The next example is a simple demonstration of the mathematics of Bayesian inference. " ] },