The class of (non-Gaussian) stable moving average processes is extende
d by introducing an appropriate joint randomization of the filter func
tion and of the stable noise, leading to stable mixed moving averages.
Their distribution determines a certain combination of the filter fun
ction and the mixing measure, leading to a generalization of a theorem
of Kanter (1973) for usual moving averages. Stable mixed moving avera
ges contain sums of independent stable moving averages, are ergodic an
d are not harmonizable. Also a class of stable mixed moving averages i
s constructed with the reflection positivity property.