Beulke Sabine, Brown Colin D
Central Science Laboratory, Sand Hutton, York YO41 1LZ, UK.
Pest Manag Sci. 2006 Jul;62(7):603-9. doi: 10.1002/ps.1198.
Monte Carlo techniques are increasingly used in pesticide exposure modelling to evaluate the uncertainty in predictions arising from uncertainty in input parameters and to estimate the confidence that should be assigned to modelling results. The approach typically involves running a deterministic model repeatedly for a large number of input values sampled from statistical distributions. A key decision in setting up a probabilistic analysis is whether there is correlation between any of the inputs to the analysis. Pesticide properties are often the most sensitive in exposure assessment. Analysis of the literature demonstrated that there are examples of both positive and negative correlation between the sorption and degradation behaviour of a pesticide, but that general trends are not apparent at present. The inclusion of even weak correlation between sorption and degradation was found to greatly influence a probabilistic analysis of leaching through soil. Correlation will reduce the predicted extent of leaching for pesticides, and it is recommended to set the correlation to zero unless the experimental data support an alternative assumption (i.e. where the correlation is statistically significant (P <or= 0.05) and experimental artefacts can be excluded).
蒙特卡罗技术在农药暴露建模中越来越多地被用于评估因输入参数的不确定性而导致的预测不确定性，并估计应赋予建模结果的置信度。该方法通常包括针对从统计分布中采样的大量输入值反复运行确定性模型。进行概率分析时的一个关键决策是分析的任何输入之间是否存在相关性。在暴露评估中，农药特性往往最为敏感。对文献的分析表明，农药的吸附和降解行为之间既有正相关的例子，也有负相关的例子，但目前尚无明显的一般趋势。研究发现，即使吸附和降解之间存在微弱的相关性，也会极大地影响通过土壤淋溶的概率分析。相关性将降低农药淋溶的预测程度，建议将相关性设为零，除非实验数据支持其他假设（即相关性具有统计学意义（P≤0.05）且可排除实验假象）。
