Production of Seabird and Marine Mammal Distribution Models for the East of Scotland
This report describes temporal and spatial patterns of density for seabird and marine mammal species in the eastern waters of Scotland from digital aerial surveys. This is important in order for the Government to make evidence-based decisions regarding the status of these species and management.
3. Glossary
Term
ππ
Description
Area of the ith photo
Term
Autocorrelation
Description
Successive items in a sequence are more similar to each other than more distant items in the sequence
Term
Covariate
Description
Explanatory variable which is continuous (e.g. distance to event)
Term
D surface
Description
Provides a summary of the relevant input data for the prediction both in terms of adjusted observed densities but also shows where there was actually survey effort (albeit not necessarily from the year in question) in that season. Predictions in regions of low survey effort should be treated with caution.
Term
Factor
Description
Explanatory variable which has a small number of discrete levels (e.g. period before or after event)
Term
GAM
Description
Generalized Additive Model - a generalized linear model in which explanatory variables take the form of smooth functions
Term
GAMM
Description
Generalized Additive Mixed Model - an extension to the generalized additive model (GAM) in which the linear predictor contains random effects in addition to the usual fixed effects.
Term
πΜππ
Description
Estimated number of individuals in each ith covered segment (corrected where necessary for availability bias) of area ai.
Term
Point estimate surfaces
Description
The predicted densities for the conditions given.
Term
Overdispersion
Description
Presence of more variability than would be expected under the assumed mean-variance relationship.
Term
2.5% and 97.5% percentile surfaces
Description
The densities of the 2.5% and 97.5% quantiles for each cell of the surface, a measure of uncertainty encompassing the range of values that the model predicts there is a 95% probability of the true mean response lying withinβ
Term
CV
Description
Coefficient of variation β measure of a dispersion of a frequency distribution calculated as the ratio of the standard deviation to the mean, expressed in percentage.
Contact
Email: REEAadmin@gov.scot
There is a problem
Thanks for your feedback