Abstract. In this paper, we present a hybrid method that combines Monte Carlo sampling and spectral methods for solving stochastic coupled problems. After partitioning the stochastic coupled problem into subsidiary subproblems, the proposed hybrid method entails iterating between these subproblems in a way that enables the use of the Monte Carlo sampling method for subproblems that depend on a very large number of uncertain parameters and the use of spectral methods for subproblems that depend on only a small or moderate number of uncertain parameters. To facilitate communication between the subproblems, the proposed hybrid method shares between the subproblems a reference representation of all the solution random variables in the form of an ensemble of samples; for each subproblem solved by a spectral method, it uses a dimension-reduction technique to transform this reference representation into a subproblem-specific reduced-dimensional representation to facilitate a computationally efficient solution in a reduced-dimensional space. After laying out the theoretical framework, we provide an example relevant to microelectomechanical systems. 1. Introduction. Coupled problems with various combinations of multiple physics, scales, and domains are found in numerous areas of science and engineering: Multiphysics models can take the form of a single equation that tightly couples different types of physical behavior, or they can take the form of a system of equations wherein the solution to certain equations is passed to other equations to determine physical properties or loadings or both. Multiscale models couple different types of behavior with fundamentally different descriptions at different scales. In multidomain models, physical behavior in different regions of space is coupled through a shared interface.Partitioned methods are widely used for solving coupled problems. These methods most often split a coupled problem into subproblems that represent single-physics, single-scale, or single-domain behavior, and they then seek a global solution by iterating between subproblem solutions. The attraction of partitioned methods is that many coupled problems afford a natural decomposition into subproblems for which computational expertise and dedicated