How to compute equation 1.68 of Bishop's book

I am trying to obtain the right hand side of equation 1.68 in Pattern Recognition and Machine Learning by Bishop. I was treating the problem as having four random variables $x,t,D,w$ where $D=(X,T)$ then I only obtain this:

$$P(t,x,D)=\int P(t,x,D,w)dw$$ $$P(t|x,D)P(x,D)=\int P(t|x,D,w)P(x,D,w)dw$$ $$P(t|x,D)=\int P(t|x,D,w)P(w|x,D)dw$$

• Please use math typesetting. math.meta.stackexchange.com/questions/5020/…
– Sycorax
Sep 26 '17 at 20:53
• We're not copyright police, but a pdf of a whole textbook seems a bit much to swallow. I've changed the link. If that makes your question harder to follow for someone without the text in front of them, note that questions are supposed to be self-contained anyway - to at least make sense without reference to external sources. Quote relevant parts if you need to. Sep 27 '17 at 8:24

Suppose we have variables $A,$ $B,$ and $C,$ and that $A$ and $B$ are conditionally independent given $C.$ This means that $P(A \mid B, C) = P(A \mid C).$ That is, if $C$ is observed, then $A$ is independent of $B.$ However, that independence is conditional, so it's still true that $P(A \mid B) \ne P(A)$ in general.
In this case, $t$ is conditionally independent of $D$ given $w.$ The reason for this is that $t$ solely depends on $w$ and $x,$ but if you don't know $w$ then $D$ gives you a hint to the value of $w.$ However, if you do know $w$ then $D$ is no longer useful for determining the value of $t.$ This explains why $D$ was omitted from $P(t \mid x, w, D)$ but not from $P(t \mid x, D).$
Similarly, $w$ is entirely independent of $x$ so $P(w \mid x, D) = P(w \mid D).$