Article ID: | iaor19921305 |
Country: | United Kingdom |
Volume: | 30 |
Issue: | 1 |
Start Page Number: | 1 |
End Page Number: | 11 |
Publication Date: | Jan 1992 |
Journal: | International Journal of Production Research |
Authors: | Muralidhar Krishnamurty, Wilson Rick L., Swenseth Scott R. |
Keywords: | simulation: applications |
The purpose of this study is to determine if the selection of the distribution used to describe processing times in JIT simulations will affect the simulation results. Three distributions that closely adhere to the requirements for describing processing times in the JIT environment are identified, namely the truncated normal, the gamma, and the log-normal distributions. The results indicate that no significant difference in performance could be attributed to the choice of the distribution, i.e. as long as the distribution selected fits closely with the requirements for describing processing times in the JIT environment, the results of the simulation study will not be affected. The gamma distribution is recommended since it specifically meets the requirements for describing processing times in the JIT environment and is computationally efficient.