Each diagonal element $G_{i,t}^r$ is specified as a logistic cumulative density functions, i.e.
$$
G_{i,t}^r(s_{i,t}^r; γ_i^r, c_i^r) = ≤ft[1 + \exp\big\{-γ_i^r(s_{i,t}^r-c_i^r)\big\}\right]^{-1}
$$
for $i = 1,2, …, \tilde{n}$ and $r=0,1,…,m-1$, so that the first model is a Vector Logistic Smooth Transition AutoRegressive (VLSTAR) model. The ML estimator of θ is obtained by solving the optimization problem
$$
\hat{θ}_{ML} = arg \max_{θ}log L(θ)
$$
where log $L(θ)$ is the log-likelihood function of VLSTAR model, given by
$$
ll(y_t|I_t;θ)=-\frac{T\tilde{n}}{2}\ln(2π)-\frac{T}{2}\ln|Ω|-\frac{1}{2}∑_{t=1}^{T}(y_t-\tilde{G}_tB\,z_t)'Ω^{-1}(y_t-\tilde{G}_tB\,z_t)
$$
The NLS estimators of the VLSTAR model are obtained by solving the optimization problem
$$
\hat{θ}_{NLS} = arg \min_{θ}∑_{t=1}^{T}(y_t - Ψ_t'B'x_t)'(y_t - Ψ_t'B'x_t).
$$