Detecting significant retrospective patterns in state space fish stock assessment

Retrospective patterns are commonly investigated to validate fish stock assessment models. A widely applied measure for retrospective bias is Mohn’s ρ and corresponding plots. However, can be interpreted differently by experts. To make decisions regarding significant less subjective, we proposed a post-sample significance test. As case studies, the state space model SAM with data on Northeast Arctic cod Norwegian coastal north of 67°N. We showed that acceptance regions depends both available complexity. also assessed test power under range assumption violations conclude useful detecting associated bias, but not variances correlations.