翻訳と辞書 |
Identifiability Analysis : ウィキペディア英語版 | Identifiability Analysis
Identifiability analysis is group of methods that are based on Mathematical statistics and can be used to estimate how well model parameters are determined by the amount and quality of experimental data. Therefore, these methods explore not only identifiability of a model as its theoretical property, but also the goodness of model relation to particular experimental data or more generally to the configuration of experiment in general. ==Introduction==
Assuming the model is defined and the regression analysis or any other model fitting could be performed to obtain the model parameters values that minimize difference between the modeled and experimental data. The goodness of fit, which represents the minimal difference between experimental and modeled data in a particular measure, does not reveal how reliable the parameter estimates are and it is not the sufficient criteria to prove the model was chosen correctly either. For example, if the experimental data was noisy or just insufficient amount of data points was processed, substitution of best fitted parameter values by orders of magnitude will not significantly influence the quality of fit. To address this issues the Identifiability analysis could be applied as an important step to ensure correct choice of model, and sufficient amount of experimental data. The purpose of this analysis is either a quantified proof of correct model choice and integrality of experimental data acquired or such analisis can serve as an instrument for the detection of non-identifiable and sloppy parameters, helping planning the experiments and in building and improvement of the model at the early stages.
抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)』 ■ウィキペディアで「Identifiability Analysis」の詳細全文を読む
スポンサード リンク
翻訳と辞書 : 翻訳のためのインターネットリソース |
Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.
|
|