This course covers the basic statistical foundation needed to follow the
discussion in a typical assessment working group. The course is inspired by
requests expressed by participants in other ICES courses and by discussions in
many expert groups. Simple small examples will be used to illustrate the
concepts of statistical modelling relevant to fish stock assessment. The format
will be to iterate between lecture, example, and exercise for each subject.
Participants should expect to learn how to draw inference from models which are
not covered by linear model routines in standard statistical software packages.
Such non-standard models are very common in natural resource assessment and
contain, for example, non-trivial non-linearities, complex covariance structures,
complicated couplings between fixed and random effects, or different sources of
observations needing different likelihood types. Further, to have a clear description/definition
and working example illustrating various standard statistical terms, such as estimator, standard deviation, variance, confidence, correlation, bias,
retrospective-bias, residual, cross-validation, prior, profile, ensemble,
bootstrap.