Analysis of biological record data: improvements of the occupancy-detection models

Many indicators are used to monitor the progress of the target which aims to stop the biodiversity loss by 2020. However, the occupancy-detection model which is currently applied to calculate the indicator is biased. Hence, more robust models are required to track the trend of the species precisely. This research first reviews the previous works on improving this occupancy-detection model by changing the prior distributions of one of the quantities and of the models considered previously, a model based on a random walk is found to be the most appropriate although it has some potential deficiencies. Then this research provides some potential improvements of the random walk model by changing the way of modelling the prior distributions of each quantity and changing the model structure. Then the hoverflies datasets are used in this research to analyse the performance of the models. These models are compared by the running times of fitting the models and the plots of the trend of the species of all models. As a result, the categorical list length model is considered to be the most precise model among all models with a reasonable running time. Then, we fit this model with a large dataset, however, it takes a long running time to get the result. Finally, some potential improvements are suggested which may be useful for further research.