金融学前沿研究R代码实现

$$r_t = c + \theta r_{t-1} + \epsilon_t$$

$$\sigma^2_t = \kappa + \alpha\sigma^2_{t-1} + \phi\epsilon^2_{t-1} + \psi[\epsilon_{t-1}<0]\epsilon^2_{t-1}$$

$$z_t = \epsilon_t/\sigma_t$$ i.i.d. distributed $$t(\nu)$$

$$
\begin{aligned}
y_{cst} &= Z^{1}_{cst} \beta^{1}_{cs} + X^{1}_{cst} \beta_{1} +\epsilon^{1}_{cst} \\
\beta^{1}_{cs} &= Z^{2}_{cs} \beta^{2}_{c} + X^{2}_{cs} \beta_{2} +\epsilon^{2}_{cs} \\
\beta^{2}_{c} &= X^{3}_{c} \beta_{3} +\epsilon^{3}_{c}.
\end{aligned}
$$