Sensitiivsusanalüüside

Sensitiivsusanalüüside, also known as sensitivity analysis, is a technique used in various fields, including economics, engineering, and environmental science, to study how the uncertainty in the output of a mathematical model or computer simulation can be attributed to different sources of uncertainty in its inputs. Essentially, it aims to understand which input variables have the most significant impact on the model's results. This helps in identifying critical parameters that require more precise estimation or control.

The process typically involves systematically varying the input parameters of a model within their plausible ranges and observing the corresponding changes in the model's output. There are various methods for conducting sensitivity analyses, ranging from simple one-at-a-time (OAT) variations to more sophisticated global methods like Sobol indices or Morris method. OAT involves changing one input parameter while keeping others fixed, which is easy to implement but may miss interactions between parameters. Global methods assess the influence of parameters and their interactions across the entire input space.

The results of a sensitivity analysis can inform decision-making by highlighting areas of high uncertainty. For instance, in project management, it can identify which project factors are most likely to cause delays or cost overruns. In policy analysis, it can help determine which assumptions are most crucial for the predicted outcomes of a proposed policy. By understanding the sensitivity of a model, researchers and practitioners can focus their efforts on improving the accuracy of the most influential inputs, thereby increasing confidence in the model's predictions and facilitating more robust decision-making.