Computational statistics

Navigation:  Statistical concepts >

Computational statistics

Previous pageReturn to chapter overviewNext page

Computational statistics is not the same as statistical computing or statistical software. It refers to the use of computational power (processing power, storage, digital displays) as a means of analyzing complex and large datasets use largely statistical procedures. It embraces a wide range of techniques and tools and draws heavily on developments in fields such as computer science, knowledge-based engineering and visualization in additional to classical statistics. Although a relatively new area of statistics, it may well become the dominant approach for addressing many categories of problem formerly addressed by traditional analysis. Examples of approaches that may be described as methods of computational statistics we would include:

data mining and advanced visualization techniques (exploratory data analysis techniques)
a wide range of simulation techniques that utilize randomization, notably Monte Carlo simulation and random permutation procedures
function and kernel density estimation
local rather than global analysis techniques (e.g. local regression techniques such as Loess and GWR, cluster hunting etc)
resampling and cross-validation of data modeling (e.g. using procedures such as jackknifing and bootstrapping)

Discussion of several of these topics is provided later in this Handbook

References

Gentle J E (2009) Computational Statistics. Springer, New York