Which estimation technique is used when dealing with significant uncertainty in time predictions?

Probabilistic estimation is particularly useful when faced with significant uncertainty in time predictions because it takes into account the variability of potential outcomes by using statistical methods. This approach allows for the assessment of different scenarios and their associated probabilities, enabling a more comprehensive understanding of the time it might take to complete a task.

By leveraging historical data and expert judgment, probabilistic estimation can provide a range of possible outcomes, which helps stakeholders to prepare for best-case, worst-case, and most likely scenarios. This technique is typically represented through methods such as Monte Carlo simulations or PERT (Program Evaluation and Review Technique), which consider the likelihood of various completion times rather than providing a single, fixed estimate.

In contrast to this methodology, a one-point estimate offers a single predicted value without accounting for uncertainty, which can be limiting. Deterministic estimation implies certainty in outcomes, hence it is less suited for scenarios with significant uncertainty. Timeboxing is a method aimed at limiting the time allocated for a task without specifically addressing uncertainty in time predictions. Therefore, probabilistic estimation stands out as the preferred technique in environments where uncertainty is high.