fix http://disq.us/p/27tcg65

docs/08-Model-Inference-and-Averaging/8.2-The-Bootstrap-and-Maximum-Likelihood-Methods.md

@@ -216,7 +216,7 @@ $$
 最大似然估计由 $\partial \ell/\partial \beta=0$ 和 $\partial \ell/\partial \sigma^2$ 给出
 $$
 \begin{align*}
-\hat\beta&=\mathbf{(H^TH)H^Ty}\\
+\hat\beta&=\mathbf{(H^TH)^{-1}H^Ty}\\
 \hat\sigma&=\frac{1}{N}\sum{(y_i-\hat\mu(x_i))^2}
 \end{align*}
 \tag{8.21}