In recent years, several papers have been written concerning the application of uncertainty analyses for isentropic compression processes under the assumption of ideal gas behavior. However, for high-pressure ratio machines, the ideal gas model fails to capture the physics of the process. Still, the estimation of test uncertainty for polytropic processes is hindered by the complexity of the equations used to calculate the performance parameters and by the incorporation of real gas equations into the models. This paper presents an uncertainty analysis developed to estimate the error levels in data gathered during factory aero-performance tests of single- or multi-stage centrifugal compressors. The analysis incorporates the effects of the variation and uncertainty levels of every parameter used to calculate centrifugal compressor aero-thermal performance. Included are the variables used to define the thermodynamic states of the fluid inside the compressor, as well as geometric and operational parameters associated with the machine and test loop. Two different methods have been utilized and the results compared to evaluate the advantages and drawbacks of each. The first method is based on the direct use of the Monte Carlo simulation technique combined with real gas equations of state. The second method employs uncertainty propagation equations and the methodology included in the ASME PTC-19.1 (1998) Test Code. Both approaches utilize the polytropic compression model and equations for performance evaluation that are included in the ASME PTC 10 (1997) Power Test Code for compressors and exhausters. The methods and results from this work may be easily extended to the isentropic compression model as well. The use of real gas equations of state make the methods applicable to virtually any gas composition. Although the analysis was intended to be applied to ASME PTC 10 Type 2 tests, the method can be extended to evaluate Type 1 and/or on-site field tests, as long as certain considerations are addressed. The uncertainty analysis presented is then used to evaluate data from several machines, ranging from a low-pressure ratio gas pipeline compressor to an eight-stage machine used for natural gas processing. Comments are offered concerning the effects of machine pressure ratio on the levels of uncertainty, as well as the importance of proper selection of instrumentation to minimize the error level of the test data. Special emphasis is placed on the benefits of using this analysis during the planning phase of the test program, to determine the optimal combination of instruments, to guarantee acceptable levels of uncertainty.