摘要
Estimation of parameters and random effects using true maximum likelihood methods is compared to the commonly used penalized maximum likelihood method. The simulated catch-at-age datasets have all conceivable noise in stock and fishing dynamics in addition to the observation error on the catch. Improvement is modest in simple models but refinements that are only possible with these methods provide additional precision. Unbiased estimation of natural mortality is made possible with these methods, but precision is low unless variation in fishing effort between years is large and other variation small, in particular the uncertainty in the recruitment. Relatively unbiased estimates of all other in-put parameters and variances were obtained. Alternately the stock may be updated with the catches directly, rather than through the fishing mortality. This can be done exactly and such that bias in the final stock is small. Such a model will test a different error structure and may also be more appealing for presentation of results as the catches are in better agreement with the changes in the estimated stock.
Estimation of parameters and random effects using true maximum likelihood methods is compared to the commonly used penalized maximum likelihood method. The simulated catch-at-age datasets have all conceivable noise in stock and fishing dynamics in addition to the observation error on the catch. Improvement is modest in simple models but refinements that are only possible with these methods provide additional precision. Unbiased estimation of natural mortality is made possible with these methods, but precision is low unless variation in fishing effort between years is large and other variation small, in particular the uncertainty in the recruitment. Relatively unbiased estimates of all other in-put parameters and variances were obtained. Alternately the stock may be updated with the catches directly, rather than through the fishing mortality. This can be done exactly and such that bias in the final stock is small. Such a model will test a different error structure and may also be more appealing for presentation of results as the catches are in better agreement with the changes in the estimated stock.
