Selecting the right-size model for prediction
β Scribed by Sholom M. Weiss; Nitin Indurkhya
- Book ID
- 104634695
- Publisher
- Springer US
- Year
- 1996
- Tongue
- English
- Weight
- 1011 KB
- Volume
- 6
- Category
- Article
- ISSN
- 0924-669X
No coin nor oath required. For personal study only.
β¦ Synopsis
We evaluate the effectiveness of cross-validation in selecting the right-size model for decision tree and k-nearest neighbor learning methods. For samples with at least 200 cases, extensive empirical evidence supports the following conclusions relative to complexity-fit selection: (a) IO-fold cross-validation is nearly unbiased; (b) ignoring model complexity-fit and picking the "standard" model is highly biased; (c) IO-fold cross-validation is consistent with optimal complexity-fit selection for large sample sizes and (d) the accuracy of complexity-fit selection by IO-fold cross-validation is largely dependent on sample size, irrespective of the population distribution.
π SIMILAR VOLUMES
## Abstract Management accountants designing an organization's performance management system face a dizzying array of costing approaches and techniques. This article describes the current βclutter in costing,β then provides a road map to help finance and accounting professionals decide which tools
We propose a classification of system models in terms of their knowledge classes and characteristics, and relate these to existing approaches to the use of AI methods in Control. Such an classification is a necessary precursor to developing a methodological approach to identifying the most appropria
## Ah&act -The phenomenon of size spreadmg of a narrow crystal-size dlstnbution (CSD) due to fluctuations 111 growth velocity was modeled usmg an eff ectlve number flux d&~s~vlty Use of tks tiusivity m the dunenslonless population balance descnbmg contmuous crystalhzer operation results m a second