Direct and indirect effects estimates
impactsSDPDm(res, NSIM = 200, sd = 12345)An object of class 'impactsSDPDm'
an object of class 'SDPDm'
number of simulations to be performed, default = 200
starting seed, default = 12345
Rozeta Simonovska
For spatial dynamic panel data model: $$y_{t} = \tau y_{t-1} + \rho W y_{t} + \eta W y_{t-1} + X_{t} \beta + W X_{t} \theta + \alpha + \mu + u_{t}$$ Short term effects for kth explanatory variable: $$(I - \rho W)^{-1}(\beta_{k} I_{n} + \theta_{k} W)$$ Long term effects for kth explanatory variable: $$((1-\tau)I_{n} - (\rho+\eta)W)^{-1}(\beta_{k} I_{n} + \theta_{k} W)$$ The direct effect is the average of the diagonal elements, and the indirect effect is the average of the row sums of the non-diagonal elements of the matrix.
SDPDm