Why does Monte Carlo simulation need thousands or millions of repeated random draws?

Conditions

• The random selection process is repeated many times.
• The selected values are stored.

Reasoning, step by step

1. Start from assumed input distributions for the uncertain quantities.
2. Randomly pick a completion time for each report from those distributions.
3. Repeat the random picking thousands or millions of times and store all selected values.
4. Use the stored results to approximate the distribution of the total time to complete both reports.

Example

The narrator says, "Now let's speed this process up and do it maybe thousands, maybe millions of times. And we're going to store all of these randomly selected values, and once we do that, we can use those stored results to approximately estimate the distribution around the time to complete both reports."

Common misconceptions

• Monte Carlo is not based on one random draw. A single random pick of completion times would already describe the total-time distribution is a misconception; the explanation stresses repeating the random selection thousands or millions of times and storing all results before estimating the output distribution.

Watch the explanation

Explore next

• How is the histogram used to estimate the total completion time distribution?
• What Python setup is shown before generating the random samples?
• How does the video compute the total time to complete both reports?