Comparing experimental design schemes in predictive food microbiology: Optimal parameter estimation of secondary models
Comparing experimental design schemes in predictive food microbiology: Optimal parameter estimation of secondary models
复制标题
比较预测食品微生物学中的实验设计方案：二级模型的最佳参数估计
DOI：
10.1016/j.jfoodeng.2012.03.018
复制
发表时间：
2012
影响因子：
5.5
通讯作者：
J. Impe
中科院分区：
文献类型：
--
作者：
L. Mertens;E. Derlinden;J. Impe
在预测食品微生物学中，全因子设计仍然是规则而不是例外，尽管这种方法涉及巨大的实验工作量和成本。在这项研究中，二次平方根型模型的模拟研究进行比较几个实验设计方面的四个标准：（i）实验数量，（ii）拟合优度统计相对于原始模型结构，（iii）准确性和（iv）参数估计的不确定性。此外，数据质量的影响，量化为与板数测量相关的误差，模型结构和实验设计之间的关系进行评估。评价全析因、简化全析因、中心复合、拉丁方和Box-Behnken设计，并与随机选择的数据集进行比较。作为指导原则，对于相当简单的模型结构和每个环境因子有限的水平数，应首选全析因设计。对于更复杂的情况，拉丁方设计是一个有吸引力的替代方案，因为它不需要先验模型知识，并提供相对准确和可靠的参数估计，同时保持最小的实验工作。
In predictive food microbiology, full factorial designs are still more the rule than the exception, despite the huge experimental workload and cost related to this method. In this study, two simulation studies for secondary square-root-type models are performed to compare several experimental designs with respect to four criteria: (i) number of experiments, (ii) goodness-of-fit statistics with respect to the original model structure, and (iii) accuracy and (iv) uncertainty of the parameter estimates. In addition, the effect of data quality, quantified as the error related to plate count measurements, is assessed on the relation between model structure and experimental design. Full factorial, reduced full factorial, central composite, Latin-square and Box-Behnken designs are evaluated and compared to randomly selected datasets. As a guideline, a full factorial design should be preferred for rather simple model structures and a limited number of levels per environmental factor. For more complex cases, a Latin-square design is an attractive alternative as it does not require a priori model knowledge and provides relatively accurate and reliable parameter estimates while keeping the experimental efforts to a minimum.