# noninformative prior (normal data)

Can someone help me through the derivation? That is, how is summation of (yi-mu)^2 equal to the equation that follows? where did n(y(bar)-mu)^2 come from?

Thanks.

• You provided half information. Can you provide more context of the data model? What is your likelihood? – Jon Aug 18 '17 at 3:53
• I'm looking at the derivation of the posterior distribution when data is normal and prior in non-informative (1/sigma^2). Likelihood is for normal iid. – Erwin Aug 18 '17 at 5:26

Take ($y_i$-$\mu$)$^2$ and add and subtract y bar inside the square and expand.