Answer: Data used for bootstrapping must be resampled with replacement.

## Explanation Bootstrapping is a resampling technique that involves drawing samples with replacement from the original dataset to create multiple simulated datasets. The key characteristics of bootstrapping are: - **Resampling with replacement**: This is the fundamental principle of bootstrapping. Each time we draw an observation from the original dataset, we put it back before drawing the next observation, allowing the same observation to appear multiple times in the bootstrap sample. - **No distributional assumptions**: Bootstrapping does not require the data to follow any specific distribution (such as normal distribution). - **Unknown properties**: Bootstrapping is particularly useful when the underlying distribution of the data is unknown or complex. - **Not exhaustive**: Bootstrapping does not require all possible outcomes to be present; it works with the available sample data. Let's analyze why the other options are incorrect: - **Option A**: Incorrect - Bootstrapping makes no assumptions about the underlying distribution of the data. - **Option B**: Incorrect - Bootstrapping works with the available sample data and doesn't require all possible outcomes to be present. - **Option D**: Incorrect - Bootstrapping is often used precisely when the properties of the variable are unknown. Therefore, option C is the correct statement about bootstrapping.

Author: LeetQuiz Editorial Team