Abstract

Softshell Dungeness Crabs have inferior meat quality and are vulnerable to handling by harvesters; therefore, knowing when softshell periods occur is important for managing Dungeness Crab fisheries. A computer simulation was used to study the effectiveness of several survey designs and statistical models for estimating softshell periods which normally would be construed from crab shell condition data obtained from trap surveys. Survey designs varied in the number of years of data collection (1, 3, 5 or 10 years) and by the number and arrangement of sampling events per year. Three statistical models, including standardized catch-per-unit-effort (SCPUE), hierarchical, and generalized additive, were tested using catch-per-unit-effort data (CPUEs) or CPUE- transformed data. CPUEs were standardised by dividing CPUE estimates by the maximum CPUE obtained in the sample year, and then transformed using the complementary log-log function. In the hierarchical model, CPUEs were modelled using a lognormal distribution, assuming the expected logarithms of CPUEs are a quadratic function of days plus a random normal error. CPUE-transformed data were modelled using a normal distribution, assuming expected values are a quadratic function of days in the SCPUE model or a spline smooth function of days in the generalized additive model. Results suggest the best survey design requires a relatively high number (6 or 11) of sampling events during several key consecutive months which contain the softshell period, and fewer sampling events during those months when softshell crab abundance is low. A minimum 3 years of data collection is required to produce reliable outputs. The hierarchical model performs best, slightly better than the SCPUE model. Use of the generalized additive model is not recommended.