Simultaneous estimation of computer model parameters and model bias.

Estimation of computer model parameters using field data is sometimes attempted in the presence of model bias. In this paper, using simulated field data, a vector-valued model bias is fit simultaneously with a scalar model calibration parameter. Our main finding is that simultaneous estimation of a bias vector and a scalar calibration parameter can be sensitive to assumptions made prior to data collection. Possible implications of this finding are considered in two examples of process monitoring for nuclear safeguards.