Statistics Masters Theses
http://hdl.handle.net/10023/662
2018-06-18T11:08:24ZDensity estimation and time trend analysis of large herbivores in Nagarhole, India
http://hdl.handle.net/10023/669
Density estimates for six large herbivore species were obtained through
analysis of line transect data from Nagarhole National Park, south-western India,
collected between 1989 and 2000. These species were Chital (Axis axis), Sambar
(Cervus unicolor), Gaur (Bos gaurus), Wild Pig (Sus scrofa), Muntjac (Muntiacus
muntjak) and Asian Elephant (Elephas maximus). Multiple Covariate Distance
Sampling (MCDS) models were used to derive these density estimates. The distance
histograms showed a relatively large spike at zero, which can lead to problems when
fitting MCDS models. The effects of this spike were investigated and remedied by
forward truncation. Density estimates from unmodified dataset were 10-15% higher
than estimates from the forward truncated data, with this going up to 37% for
Muntjac. These could possibly be over estimates. Empirical trend models were then
fit to the density estimates. Overall trends were stable, though there were intra-habitat
differences in trends for some species. The trends were similar both in cases where
forward truncation was done as well as in those where they were not.
MRes in Environmental Biology
2005-01-01T00:00:00ZGangadharan, AdityaDensity estimates for six large herbivore species were obtained through
analysis of line transect data from Nagarhole National Park, south-western India,
collected between 1989 and 2000. These species were Chital (Axis axis), Sambar
(Cervus unicolor), Gaur (Bos gaurus), Wild Pig (Sus scrofa), Muntjac (Muntiacus
muntjak) and Asian Elephant (Elephas maximus). Multiple Covariate Distance
Sampling (MCDS) models were used to derive these density estimates. The distance
histograms showed a relatively large spike at zero, which can lead to problems when
fitting MCDS models. The effects of this spike were investigated and remedied by
forward truncation. Density estimates from unmodified dataset were 10-15% higher
than estimates from the forward truncated data, with this going up to 37% for
Muntjac. These could possibly be over estimates. Empirical trend models were then
fit to the density estimates. Overall trends were stable, though there were intra-habitat
differences in trends for some species. The trends were similar both in cases where
forward truncation was done as well as in those where they were not.Models of random wildlife movement with an application to distance sampling
http://hdl.handle.net/10023/668
In this paper we present three models of random wildlife movement: a one dimensional model of wildlife-observer encounters on roads, an analogous two dimensional model, and an further two-dimensional model that borrows from the ideas of statistical mechanics. We then derive unbiased estimates of wildlife density in terms of encounters for each of these models. By extending these results to incorporate uncertain detection, we suggest three novel distance sampling methods and briefly consider possible field applications.
2007-01-01T00:00:00ZDiTraglia, Francis J.In this paper we present three models of random wildlife movement: a one dimensional model of wildlife-observer encounters on roads, an analogous two dimensional model, and an further two-dimensional model that borrows from the ideas of statistical mechanics. We then derive unbiased estimates of wildlife density in terms of encounters for each of these models. By extending these results to incorporate uncertain detection, we suggest three novel distance sampling methods and briefly consider possible field applications.Designing a shipboard line transect survey to estimate cetacean abundance off the Azores Archipelago, Portugal
http://hdl.handle.net/10023/667
Management schemes dedicated to the conservation of wildlife populations rely on the effective monitoring of population size, and this requires the accurate and precise estimation of abundance. The accuracy and precision of estimates are determined to a large extent by the survey design. Line transect surveys are commonly applied to wildlife population assessments in which the primary purpose of a survey design is to ensure that the critical distance sampling assumptions are met.
Little information is available regarding cetacean abundance in the Archipelago of the Azores (Portugal). This study aims to design a line transect shipboard survey that allows the collection of data required to provide abundance estimates for such species. Several aspects must be taken into consideration when designing a survey to estimate cetacean abundance. This is an iterative process, and there is a constant trade off between the logistic constraints and the desired statistical robustness. Information on this process is provided to aid policy makers and environmental managers, such as the criteria used for the choices made when defining the elements of a survey design.
Three survey effort scenarios are provided to illustrate the range of possibilities between statistical robustness and logistic/ management restrictions. A survey is designed for the more economical scenario (L=5000Km), although the second scenario is the one recommended to be implemented (L=17,600Km) given it provides robust estimates of
abundance (CV<=0.2).
Revised version November 2008. MRes in Marine Mammal Science
2008-01-01T00:00:00ZFaustino, ClĂˇudia Estevinho SantosManagement schemes dedicated to the conservation of wildlife populations rely on the effective monitoring of population size, and this requires the accurate and precise estimation of abundance. The accuracy and precision of estimates are determined to a large extent by the survey design. Line transect surveys are commonly applied to wildlife population assessments in which the primary purpose of a survey design is to ensure that the critical distance sampling assumptions are met.
Little information is available regarding cetacean abundance in the Archipelago of the Azores (Portugal). This study aims to design a line transect shipboard survey that allows the collection of data required to provide abundance estimates for such species. Several aspects must be taken into consideration when designing a survey to estimate cetacean abundance. This is an iterative process, and there is a constant trade off between the logistic constraints and the desired statistical robustness. Information on this process is provided to aid policy makers and environmental managers, such as the criteria used for the choices made when defining the elements of a survey design.
Three survey effort scenarios are provided to illustrate the range of possibilities between statistical robustness and logistic/ management restrictions. A survey is designed for the more economical scenario (L=5000Km), although the second scenario is the one recommended to be implemented (L=17,600Km) given it provides robust estimates of
abundance (CV<=0.2).Behavioural changes of a long-ranging diver in response to oceanographic conditions
http://hdl.handle.net/10023/665
The development of an animal-borne instrument that can record oceanographic measurements (CTD-SRDL) has enabled the collection of oceanographic data at a scale relevant to the counterpart behavioural data, both in time and 3-dimensional space. This has advanced the potential for studies of the behaviour of deep-diving marine animals and the way in which they respond to their environment, yet the nature of the data delivered by CTD-SRDLs presents substantial analytical challenges and places constraints on its biological interpretation. Behavioural and environmental data, collected using CTD-SRDLs deployed on southern elephant seals (Mirounga leonina) from the South Georgia subpopulation in 2004 and 2005, are analysed for 13 females and 4 males (21,015 dives). Compressed dive profiles are used to classify individual dives into six distinct types based on their 2-dimensional time-depth characteristics using random forest classification. The relationship between dive type and environmental variables, derived from oceanographic data recorded on board the animals, is investigated in the context of regression analysis, employing a multinomial model, as well as independently fitted Generalized Linear Models (GLM) and Generalized Additive Models (GAM) for each dive type. Regression is not found to be an appropriate method for analysing abstracted behavioural dive data, and other methods are suggested. We show that functional specializations can be manifested within a dive type, using square bottom dives (SQ) as an example. The usefulness of dive classification is discussed in the context of behavioural interpretation, and validity of the ecological functions attached to each class. Preliminary analyses are important drivers of further research into improving the interpretability of abstracted behavioural data, and developing efficient, standardized methods for widespread application to this type of data, which is obtained in abundance via satellite telemetry.
BL 5019 Research project. MRes Environmental Biology
2007-01-01T00:00:00ZPhotopoulos, TheoniThe development of an animal-borne instrument that can record oceanographic measurements (CTD-SRDL) has enabled the collection of oceanographic data at a scale relevant to the counterpart behavioural data, both in time and 3-dimensional space. This has advanced the potential for studies of the behaviour of deep-diving marine animals and the way in which they respond to their environment, yet the nature of the data delivered by CTD-SRDLs presents substantial analytical challenges and places constraints on its biological interpretation. Behavioural and environmental data, collected using CTD-SRDLs deployed on southern elephant seals (Mirounga leonina) from the South Georgia subpopulation in 2004 and 2005, are analysed for 13 females and 4 males (21,015 dives). Compressed dive profiles are used to classify individual dives into six distinct types based on their 2-dimensional time-depth characteristics using random forest classification. The relationship between dive type and environmental variables, derived from oceanographic data recorded on board the animals, is investigated in the context of regression analysis, employing a multinomial model, as well as independently fitted Generalized Linear Models (GLM) and Generalized Additive Models (GAM) for each dive type. Regression is not found to be an appropriate method for analysing abstracted behavioural dive data, and other methods are suggested. We show that functional specializations can be manifested within a dive type, using square bottom dives (SQ) as an example. The usefulness of dive classification is discussed in the context of behavioural interpretation, and validity of the ecological functions attached to each class. Preliminary analyses are important drivers of further research into improving the interpretability of abstracted behavioural data, and developing efficient, standardized methods for widespread application to this type of data, which is obtained in abundance via satellite telemetry.