In a previous blog we noted that the two-dimensional “dart board” method can be used to compare the efficacy of Monte Carlo (MC) and Latin Hypercube (LH) sampling methods, by using it to estimate the value of π (3.14159…). This can be generalised to create more representative tests that apply to multi-variable models that would generally be used in practice.
Archives for April 2015
Simulation and risk modelling are often thought of as equivalent, since in most business contexts the application of simulation methods is almost always to risk assessment; conversely, quantitative risk assessment often requires the use of simulation. However, there are some differences between the two.
The blog briefly mentions some risks in using linked Excel workbooks when building models, as well as some techniques that may be used to minimise the materialisation of such risks.