EFFECT OF UNCERTAINTY IN INPUT AND PARAMETER VALUES ON MODEL PREDICTION ERROR

Uncertainty in input or parameter values affects the quality of model predictions. Uncertainty analysis attempts to quantify these effects. This is important, first of all as part of the overall investigation i nto model predictive quality and secondly in order to know if addition al or more precise measurements are worthwhile. Here, two particular a spects of uncertainty analysis are studied. The first is the relations hip of uncertainty analysis to the mean squared error of prediction (M SEP) of a model. It is shown that uncertainty affects the model bias c ontribution to MSEP, but this effect is only due to non linearities in the model. The direct effect of variability is on the model variance contribution to MSEP. It is shown that uncertainty in the input variab les always increases model variance. Similarly, model variance is alwa ys larger when one averages over a range of parameter values, as compa red with using the mean parameter values. However, in practice, one is usually interested in the model with specific parameter values. In th is case, one cannot draw general conclusions in the absence of detaile d assumptions about the correctness of the model. In particular, certa in particular parameter values could give a smaller model variance tha n that given by the mean parameter values. The second aspect of uncert ainty analysis that is studied is the effect on MSEP of having both li terature-based parameters and parameters adjusted to data in the model . It is shown that the presence of adjusted parameters in general, dec reases the effect of uncertainty in the literature parameters. To illu strate the theory derived here, we apply it to a model of sugar accumu lation in fruit. (C) 1998 Elsevier Science B.V.