Mixed data sampling

From Wikipedia, the free encyclopedia

Mixed data sampling (MIDAS) is an econometric model developed by Ghysels et al. in which the regressor appears at a higher frequency than the regressand:

$y_{t}=\beta_{0}+\beta_{1}B(L^{1/m};\theta)x_{t}^{(m)}+\epsilon_{t}^{(m)},\,$

where y is the regressand, x is the regressor, m denotes the frequency - for instance if y is yearly $x_{t}^{(4)}$ is quarterly - $ε$ is the disturbance and $B (L 1 / m;θ)$ is a lag distribution, for instance the Beta function or the Almon lag.