In: Statistics and Probability
Q 3b18.
After determining an appropriate warm up period, run length, and run strategy, Nico Case conducts a set of experiments with her model.
a.) In the first set of experiments, she runs her model for 5 replications of one-year, following a 30 day warm up, under the strategy of batch means. Assume that a one-year period is sufficient for statistical purposes. The monthly throughput from her model is 6,000 units/month and the standard deviation is 50. Approximately how many replications are required if Ms. Case wants her experiments to be powered to detect a difference in monthly throughput of 15 units, 19 times out of 20?
b.) Assume that Ms. Case has run her model for 5 replications of 30 days, following a 30-day warm up period. The average monthly throughput from her model is N (6104, 70). The system vendor indicates that a similar system installed in Whitby, ON is known to have a monthly throughput of 6053 units. No standard deviation is provided by the vendor. What can you say about Nico's model, with relation to the vendor estimates?
c.) As a final test of validity, Ms. Case adjusts her model to make it representative of her firm's current warehouse layout and logistics. She runs her model for 6 replications of one year and calculates the monthly throughput. She also obtains a sample of data from her firm's warehouse for the previous 6 months.
Simulation |
Warehouse |
|
Month 1 |
4040 |
4060 |
Month 2 |
4020 |
4060 |
Month 3 |
4005 |
4051 |
Month 4 |
4001 |
4024 |
Month 5 |
4046 |
4028 |
Month 6 |
3977 |
4061 |
Is there any evidence that the simulation is representative of the existing warehouse?
NOTE: This question is for Industrial Engineering stream for Simulation & Modelling Analysis subject. There is no options given in drop down menu for IE and selected for ME stream. Please help in answering all a, b, and c section.
In this paper, we examine the use of exponentially weighted moving average (EWMA) control charts for the detection of initialization bias in steady state simulation experiments. EWMA charts have the interesting property of being more sensitive to shifts in the data as compared to other control charting techniques. We exploit this sensitivity by developing a criteria for searching for the deletion point when the EWMA is applied to the reversed data sequence. This allows us to more easily detect and count the number of times the smoothed sequence remains in control. Our results indicate that the procedure can quickly find and recommend a deletion point. In addition, the properties of the resulting estimators are good if the dataset that is being analyzed does not have an overtly large amount of biased data points. We use experimental test cases to illustrate the properties of the procedure.