ENH: Implement Bootstrapping for Confidence Interval Estimation

[Gui-FernandesBR]

Is your feature request related to a problem? Please describe.
Currently, the MonteCarlo class calculates basic statistics (mean and standard deviation) for simulation results. However, users lack a metric to evaluate the reliability of these statistics.

Without confidence intervals, it is difficult to determine if the sample size (number of simulations) is sufficient. Users need a way to quantify the uncertainty of their results (e.g., "We are 95% confident the true mean apogee is between X and Y").

Describe the solution you'd like
Implement a method within the MonteCarlo class that uses Bootstrapping (resampling with replacement) to estimate confidence intervals for simulation outputs.

Implementation Details

• Target File: rocketpy/simulation/monte_carlo.py
• Recommended Approach: Use scipy.stats.bootstrap (preferred for robustness) or numpy random choice to resample the data stored in self.results.
• New Method: Create a method likely named calculate_confidence_interval or estimate_ci.

Proposed Usage

# After running simulations
analysis = MonteCarlo(...)
analysis.simulate(number_of_simulations=500)

# Calculate 95% CI for Apogee
ci_result = analysis.calculate_confidence_interval(
    variable="apogee", 
    confidence_level=0.95, 
    method="BCa" # or 'percentile'
)

print(f"95% CI for Apogee: {ci_result.low} to {ci_result.high}")

Acceptance Criteria

• Implement a method to calculate Confidence Intervals (CI) for any scalar output variable (e.g., apogee, impact_velocity).
• Allow the user to specify the confidence level (default to 0.95).
• Add unit tests to verify the statistical bounds are reasonable.
• Update documentation with a brief explanation of how to interpret the CI.

Additional Context

• Reference: [Scipy Bootstrap Documentation](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.bootstrap.html)