Analysis of spatial variability of Georges Bank haddock (Melanogrammus aeglefinus) from trawl survey data using a linear regression model with spatial interaction

A regression model with spatially autocorrelated errors used to test if there is systematic spatial variation the study area in haddock catch per tow data from the annual fall survey from 1963 - 1987. A maximum estimation procedure is used, and the likelihoodratio is used for testing the significance of the. The results suggest that for many of the years information on the depth and location of sampling can be used to explain part of the spatial of the trawl catches. If model-based inferences made from the survey data, the depth related trend and autocorrelation for the errors of the model should be into account. The potential use of a spatial method for geographic mapping of density is.