Scenario-based stochastic programming (SBSP) methods have been used broadly to cope with power system operation and planning uncertainties. For SBSP, probability density functions (PDFs) of uncertain parameters must be known and many scenarios are typically generated to precisely approximate the PDFs causing computational burden. On the other hand, uncertainties via fuzzy programming methods can be handled without knowing the related PDFs by considering fuzzy numbers. However, the respective solutions depend on the value of $\alpha$-cut. As a result, to mitigate the aforementioned drawbacks and to exploit the benefits of both fuzzy optimization and SBSP, a novel hybrid fuzzy-stochastic programming model is proposed to model uncertainty in the day-ahead scheduling of isolated microgrids. A modified IEEE 33-bus test system is deployed as a case study to analyze the applicability of the proposed model, which was implemented in AMPL and solved using CPLEX solver. The comparison of results for the deterministic, the fuzzy programming, and the proposed method demonstrates that the proposed hybrid method enhanced the fuzzy programming model and guaranteed the robustness of the solutions by slightly increasing the total cost of the microgrid by 2.3%.