Statistical design of experiments is widely used among scientists and engineers to understand influential factors in a laboratory or manufacturing process. One of the underlying principles of using the statistical design of experiments method is randomisation, each run of experimental settings will be determined completely unsystematically. In practice, especially in a complicated process that consists of multiple stages, randomisation may pose too high a burden on time and cost.In this study, the multistage fraction factorial split plot design is proposed for green yield improvement in a lost mould rapid infiltration process that has been developed to fabricate zirconia ceramic parts. This design allows a relaxation of the randomisation principle so that certain experimental runs can be carried out in convenient groups. The results indicate that the type of immersion chemical and mould coating play a role in improving process yield. Additionally, the results suggest that a mould infiltration machine should be used to improve the reproducibility of the process.