North American Breeding Bird Survey status and trend estimates to inform a wide range of conservation needs, using a flexible Bayesian hierarchical generalized additive model

The status and trend estimates derived from the North American Breeding Bird Survey (BBS) are critical sources of information for bird conservation. However, the estimates are partly dependent on the statistical model used. Therefore, multiple models are useful because not all of the varied uses of these estimates (e.g., inferences about long-term change, annual fluctuations, population cycles, and recovery of once-declining populations) are supported equally well by a single statistical model. Here we describe Bayesian hierarchical generalized additive models (GAMs) for the BBS, which share information on the pattern of population change across a species’ range. We demonstrate the models and their benefits using data from a selection of species, and we run full cross-validation of the GAMs against 2 other models to compare the predictive fit. The GAMs have a better predictive fit than the standard model for all species studied here and comparable predictive fit to an alternative first difference model. In addition, one version of the GAM described here (GAMYE) estimates a population trajectory that can be decomposed into a smooth component and the annual fluctuations around that smooth component. This decomposition allows trend estimates based only on the smooth component, which are more stable between years and are therefore particularly useful for trend-based status assessments, such as those by the International Union for the Conservation of Nature. It also allows for the easy customization of the model to incorporate covariates that influence the smooth component separately from those that influence annual fluctuations (e.g., climate cycles vs. annual precipitation). For these reasons and more, this GAMYE model is a particularly useful model for the BBS-based status and trend estimates.

Modeling misretrieval and feature substitution in agreement attraction: A computational evaluation

We present a self-paced reading study investigating attraction effects on number agreement in Eastern Armenian. Both word-by-word reading times and open-ended responses to sentence-final comprehension questions were collected, allowing us to relate reading times and sentence interpretations on a trial-by-trial basis. Results indicate that readers sometimes misinterpret the number feature of the subject in agreement attraction configurations, which is in line with agreement attraction being due to memory encoding errors. Our data also show that readers sometimes misassign the thematic roles of the critical verb. While such a tendency is principally in line with agreement attraction being due to incorrect memory retrievals, the specific pattern observed in our data is not predicted by existing models. We implement four computational models of agreement attraction in a Bayesian framework, finding that our data are better accounted for by an encoding-based model of agreement attraction, rather than a retrieval-based model. A novel contribution of our computational modeling is the finding that the best predictive fit to our data comes from a model that allows number features from the verb to overwrite number features on noun phrases during encoding.

North American Breeding Bird Survey status and trend estimates to inform a wide-range of conservation needs, using a flexible Bayesian hierarchical generalized additive model

ABSTRACTThe status and trend estimates derived from the North American Breeding Bird Survey (BBS), are critical sources of information for bird conservation. However, the estimates are partly dependent on the statistical model used. Therefore, multiple models are useful because not all of the varied uses of these estimates (e.g. inferences about long-term change, annual fluctuations, population cycles, recovery of once declining populations) are supported equally well by a single statistical model. Here we describe Bayesian hierarchical generalized additive models (GAM) for the BBS, which share information on the pattern of population change across a species’ range. We demonstrate the models and their benefits using data a selection of species; and we run a full cross-validation of the GAMs against two other models to compare predictive fit. The GAMs have better predictive fit than the standard model for all species studied here, and comparable predictive fit to an alternative first difference model. In addition, one version of the GAM described here (GAMYE) estimates a population trajectory that can be decomposed into a smooth component and the annual fluctuations around that smooth. This decomposition allows trend estimates based only on the smooth component, which are more stable between years and are therefore particularly useful for trend-based status assessments, such as those by the IUCN. It also allows for the easy customization of the model to incorporate covariates that influence the smooth component separately from those that influence annual fluctuations (e.g., climate cycles vs annual precipitation). For these reasons and more, this GAMYE model is a particularly useful model for the BBS-based status and trend estimates.LAY SUMMARYThe status and trend estimates derived from the North American Breeding Bird Survey are critical sources of information for bird conservation, but they are partly dependent on the statistical model used.We describe a model to estimate population status and trends from the North American Breeding Bird Survey data, using a Bayesian hierarchical generalized additive mixed-model that allows for flexible population trajectories and shares information on population change across a species’ range.The model generates estimates that are broadly useful for a wide range of common conservation applications, such as IUCN status assessments based on trends or changes in the rates of decline for species of concern; and the estimates have better or similar predictive accuracy to other models., and

Evaluation of design flood estimates – a case study for Norway

The aim of this study was to evaluate the predictive fit of probability distributions to annual maximum flood data, and in particular to evaluate (1) which combination of distribution and estimation method gives the best fit and (2) whether the answer to (1) depends on record length. These aims were achieved by assessing the sensitivity to record length of the predictive performance of several probability distributions. A bootstrapping approach was used by resampling (with replacement) record lengths of 30 to 90 years (50 resamples for each record length) from the original record and fitting distributions to these subsamples. Subsequently, the fits were evaluated according to several goodness-of-fit measures and to the variability of the predicted flood quantiles. Our initial hypothesis that shorter records favor two-parameter distributions was not clearly supported. The ordinary moments method was the most stable while providing equivalent goodness-of-fit.