Sampling (computational modeling)

In computational modeling and computer experiments, sampling is a process of data generation, which is commonly used for Monte Carlo simulation and uncertainty analysis, global sensitivity analysis and other sensitivity and design of experiments studies, for example with heat maps and response surfaces.

Methods

The sampling strategies include different techniques.

1. Simple random sampling is the most common method used for Monte Carlo simulation. Simple random sampling can be implemented in any programming language and spreadsheet environment with a straightforward rand function or its variations.
2. Latin hypercube sampling is a simple approach that attempts to improve coverage of the multidimensional space compared to simple random sampling but does not always outperform it.
3. Quasi-random sampling attempts to feel the multidimensional space more uniformly by utilizing low-discrepancy sequences, among which Sobol' sequences are found the best performing. Quasi-random sampling functionality is available in Python, R, Julia, and Matlab.
4. Full factorial design involves choosing several points for each input variable and then evaluating the model for all their combinations. The computational complexity of this method grows exponentially with the number of input variables involved. Various fractional factorial design methods have been introduced to improve the computational efficiency of the approach.