The fitting of dynamic models to observed data
β Scribed by John V. Huddleston
- Publisher
- Springer
- Year
- 1976
- Tongue
- English
- Weight
- 301 KB
- Volume
- 38
- Category
- Article
- ISSN
- 1522-9602
No coin nor oath required. For personal study only.
β¦ Synopsis
The question of how to fit a general cubic model of a multicomponent, interactive growth system to observed data is addressed. A multidimensional-polynomial type of regression analysis is used, with a least-squares criterion. By testing the scheme on a problem with known solution, the way in which the accuracy of the results varies with the number of datum points used is investigated in an heuristic manner.
π SIMILAR VOLUMES
The paper reviews many of the techniques used to choose the most appropriate model order when fitting a choice of models to available data. The goodness-of-fit test alone is often inadequate, since models with too many parameters can appear to fit the data better, but the improved fit does not carry
Estimation of parameters in a genetic model can be very difficult using likelihood theory when there is no concise functional form for the likelihood function. An alternative method bawd on fitting the characteristic function is suggested and this method may be used on data with consistent familial