Significant variation in results for breakdown data in different reps?

Hi Team,

I am working on simulation where I need to feed the following breakdown data, but it is causing significant variation in end results of mean repair time. Currently, I am running this model for 365 days and it is generating minimum 154 data points in rep 2.

I am worried on accuracy as we are not close to mean time of 84 mins in many reps. How to interpret this data?

Is there any way to improve it further?

Please find the model attached for your reference.

Breakdown_Count_Reps.fsm

Thanks!

Software Version:

FlexSim 23.2.0

· 8

5 |100000

Attachments: Up to 12 attachments (including images) can be used with a maximum of 23.8 MiB each and 47.7 MiB total.

Felix Möhlmann commented · Dec 09 at 08:31 AM

By generating a couple million values from the distribution it seems that getting an average of more than 110 with 184 samples has a change of about 0.2%. More than 105 and 100 are aorund 0.9% and 3.2% respectively.

It seems like you got very "lucky" with the results of the replications. You could possibly argue to disregard the replication 7 as an unlikely statistical outlier.

0 ·

Ankur A3 Felix Möhlmann commented · Dec 09 at 01:34 PM

Hi @Felix Möhlmann,

Thanks for your answer! it makes sense for me.

Going further, should I exclude the outlier manually as it shows the avg value of all data points in results table?

I think it will be little time consuming to do it manually when there are more scenarios and performance metrics. What would you suggest?

Thank you!

0 ·

1733751161999.png (64.5 KiB)

Felix Möhlmann Ankur A3 commented · Dec 09 at 02:31 PM

From version 24.0 onwards, the experimenter has a filter which can filter out replications based on performance measures or parameters. If you have an active license for that version, upgrading might not be a bad idea.

In 23.2 deleting the respective replication manually would be the only option.

Another thing I just realized is that the distribution you are using is somewhat likely to return negative numbers. Since breakdown times would be 0 in those cases, the average of the down times will be higher than the mean of the distribution. With that taken into account the chances for the results are around 1.5 times as high as I initially tested.

0 ·

Show more comments

Logan Gold ♦♦ commented · Dec 13 at 04:53 PM

Hi @Ankur A3, was undefined helpful? If so, please click the "Accept" button at the bottom of their answer. Or if you still have questions, add a comment and we'll continue the conversation.

If we haven't heard back from you within 3 business days we'll auto-accept an answer, but you can always comment back to reopen your question.

0 ·