2016
Distance sampling is a widely used group of closely related methods for estimating the density and/or abundance of biological populations. The main methods are line-transect sampling and point-transect sampling (also called variable circular plot sam-pling). These have been used successfully in a very diverse array of taxa, including trees, shrubs and herbs, insects, amphibians, reptiles, birds, fish, and marine and land mammals. In both cases, the basic idea is the same. One or more observers perform a standardized survey along a randomly located set of lines or points, searching for objects of interest (usually animals or clusters of animals). For each object detected, they record the distance from the line or point to the object. Not all the objects will be detected, but a fundamental assumption of the basic methods is that all objects that are actually on the line or point are detected. Intuitively, one would expect that objects become harder to detect with increasing distance from the line or point, resulting in fewer detections with increasing distance. The key to dis-tance sampling analyses is to fit a detection function to the observed distances, and use this fitted function to estimate the proportion of objects missed during the survey. From here, we can readily obtain point and interval estimates for the density and abundance of objects in the survey area. The basic methods (sometimes called standard or conventional distance sampling) are described in detail in Ref. 1, which is an updated version of Ref. 2. Various extensions and more advanced methods are considered in Ref. 3. Free software, Distance [4], provides for the design and analysis of distance sampling surveys, imple-menting the methods described in Ref. 1 and many of those in Ref. 3. Distance sampling is an extension of quadrat-based sampling methods. Two forms of quadrat sam-pling are strip transects, in which one or more observers move along a line, counting all objects within a predetermined distance of the line, and point
Cited by 0
S. T. Buckland, David R. Anderson, Kenneth P. Burnham et al. · Encyclopedia of Biostatistics · 2005
Abstract Distance sampling covers a range of methods in which distances of detected objects (usually animals) from a line or point are recorded, from which object density or abundance is estimated. The most widely used methods are line transect sampling and point transect sampling. Objects on the line or point are usually assumed to be detected with certainty, and a detection function, representing probability of detection as a function of distance from the line or point, is modeled. This allows estimation of the proportion of objects missed within surveyed strips or circles, extending a specified distance from the line or point. Appropriate survey design allows the resulting object density estimates to be extrapolated to the full survey region, to yield estimates of object abundance.
Cited by 126
David L. Borchers, S. T. Buckland, W. Zucchini · Statistics in the health sciences · 2002
Cited by 0
Tiago A. Marques, S. T. Buckland, David L. Borchers et al. · International Encyclopedia of Statistical Science · 2011
Cited by 8
Valeria Leticia Martin-Albarracin · Figshare · 2015
Dataset of direct censuses of terrestrial vertebrates for distance sampling analyses on Isla Victoria, Nahuel Huapi National Park.
Cited by 0Open access
J. H. Pollard · St Andrews Research Repository (St Andrews Research Repository) · 2002
We investigate mechanisms to improve efficiency for line and point transect surveys of clustered populations by combining the distance methods with adaptive sampling. In adaptive sampling, survey effort is increased when areas of high animal density are located, thereby increasing the number of observations. We begin by building on existing adaptive sampling techniques, to create both point and line transect adaptive estimators, these are then extended to allow the inclusion of covariates in the detection function estimator. However, the methods are limited, as the total effort required cannot be forecast at the start of a survey, and so a new fixed total effort adaptive approach is developed. A key difference in the new method is that it does not require the calculation of the inclusion probabilities typically used by existing adaptive estimators. The fixed effort method is primarily aimed at line transect sampling, but point transect derivations are also provided. We evaluate the new methodology by computer simulation, and report on surveys of harbour porpoise in the Gulf of Maine, in which the approach was compared with conventional line transect sampling. Line transect simulation results for a clustered population showed up to a 6% improvement in the adaptive density variance estimate over the conventional, whilst when there was no clustering the adaptive estimate was 1% less efficient than the conventional. For the harbour porpoise survey, the adaptive density estimate cvs showed improvements of 8% for individual porpoise density and 14% for school density over the conventional estimates. The primary benefit of the fixed effort method is the potential to improve survey coverage, allowing a survey to complete within a fixed time and effort; an important feature if expensive survey resources are involved, such as an aircraft, crew and observers.
Cited by 1
S. T. Buckland, David R. Anderson, K P Burnham et al. · 2004
Abstract This advanced text focuses on the uses of distance sampling to estimate the density and abundance of biological populations. It addresses new methodologies, new technologies and recent developments in statistical theory and is the follow up companion to Introduction to Distance Sampling (OUP, 2001). In this text, a general theoretical basis is established for methods of estimating animal abundance from sightings surveys, and a wide range of approaches to analysis of sightings data is explored. These approaches include: modelling animal detectability as a function of covariates, where the effects of habitat, observer, weather, etc. on detectability can be assessed; estimating animal density as a function of location, allowing for example animal density to be related to habitat and other locational covariates; estimating change over time in populations, a necessary aspect of any monitoring programme; estimation when detection of animals on the line or at the point is uncertain, as often occurs for marine populations, or when the survey region has dense cover; survey design and automated design algorithms, allowing rapid generation of sound survey designs using geographic information systems; adaptive distance sampling methods, which concentrate survey effort in areas of high animal density; passive distance sampling methods, which extend the application of distance sampling to species that cannot be readily detected in sightings surveys, but can be trapped; and testing of methods by simulation, so that performance of the approach in varying circumstances can be assessed. Authored by a leading team this text is aimed at professionals in government and environment agencies, statisticians, biologists, wildlife managers, conservation biologists and ecologists, as well as graduate students, studying the density and abundance of biological populations.
Cited by 807
Alice Richardson · Ecology · 2008
Buckland, S. T., D. R. Anderson, K. P. Burnham, J. L. Laake, D. L. Borchers, and L. Thomas. 2007. Advanced distance sampling. Oxford University Press, New York. xvii + 416 p. £59.00 (cloth), ISBN: 978‐0‐19‐850783‐3 (alk. paper); £29.95 (paper), ISBN: 978‐0‐19‐922587‐3 (alk. paper).
Cited by 29
Valeria Leticia Martin-Albarracin · Figshare · 2015
Dataset of direct censuses of terrestrial vertebrates for distance sampling analyses on Isla Victoria, Nahuel Huapi National Park.
Cited by 0Open access
Valeria leticia Martin-albarracin · Figshare · 2015
Dataset of direct censuses of terrestrial vertebrates for distance sampling analyses on Isla Victoria, Nahuel Huapi National Park.
Cited by 0Open access
2016
where a and b are twomultivariate observations, Σ− is the inverse of the variance-covariance matrix and (a − b) ′ is the transpose of vector (a − b). e Mahalanobis distance is designed to take into account the correlation between all variables (attributes) of the observations under consideration. For uncorre-lated variables, the Mahalanobis distance reduces to the Euclidean distance for standardized data. As an example, consider a set of points x inR that have the constant distance r from the origin, that is, (, ).en, the set of points having the property dMahalanobis(, x) = r is an ellipse.eMahalanobis distance is a positive denite quadratic form x′Ax, where the matrix A = Σ−. Distance measures or metrics are members of a broader concept called similarity measures (or dissimi-
Cited by 0
S. T. Buckland, Eric A. Rexstad, Tiago A. Marques et al. · Methods in statistical ecology · 2015
Cited by 3
Laura J. Marshall · 2021
Performs distance sampling simulations. 'dsims' repeatedly generates instances of a user defined population within a given survey region. It then generates realisations of a survey design and simulates the detection process. The data are then analysed so that the results can be compared for accuracy and precision across all replications. This process allows users to optimise survey designs for their specific set of survey conditions. The effects of uncertainty in population distribution or parameters can be investigated under a number of simulations so that users can be confident that they have achieved a robust survey design before deploying vessels into the field. The distance sampling designs used in this package from 'dssd' are detailed in Chapter 7 of Advanced Distance Sampling, Buckland et. al. (2008, ISBN-13: 978-0199225873). General distance sampling methods are detailed in Introduction to Distance Sampling: Estimating Abundance of Biological Populations, Buckland et. al. (2004, ISBN-13: 978-0198509271). Find out more about estimating animal/plant abundance with distance sampling at <<a href="https://distancesampling.org/" target="_top">https://distancesampling.org/</a>>.
Cited by 3Open access
P.G. McLaren · Proceedings of the Institution of Electrical Engineers · 1968
A sampling technique has been developed which allows a comparison of instantaneous values derived at different instants of time, thereby dispensing with the need to phase-shift or mix signals derived from the primary line quantities. Both amplitude and phase comparisons are used to derive a variety of impedance characteristics. The relays combine high sensitivity with a high resistance to interference. Detailed results are presented for a current-polarised relay with a characteristic surrounding the probable fault area.
Cited by 15
S L Hedley, S. T. Buckland, David L. Borchers · 2004
Abstract Increasingly, wildlife managers wish to extract more than just an abundance estimate from their sightings surveys. They frequently need to relate animal density to spatial variables reflecting topography, habitat, and other factors that affect the animals’ environment. This aids assessment of how to manage that environment, and the animals within it. There is therefore a strong demand for spatial models for analysing line transect data.
Cited by 40
Marc Kéry, J. Andrew Royle · Elsevier eBooks · 2015
Cited by 2
David Miller, T.J. Clark-Wolf · 2012
A simple way of fitting detection functions to distance sampling data for both line and point transects. Adjustment term selection, left and right truncation as well as monotonicity constraints and binning are supported. Abundance and density estimates can also be calculated (via a Horvitz-Thompson-like estimator) if survey area information is provided. See Miller et al. (2019) <<a href="https://doi.org/10.18637%2Fjss.v089.i01" target="_top">doi:10.18637/jss.v089.i01</a>> for more information on methods and <<a href="https://distancesampling.org/resources/vignettes.html" target="_top">https://distancesampling.org/resources/vignettes.html</a>> for example analyses.
Cited by 49Open access
S. T. Buckland, David R. Anderson · 2004
Abstract Distance sampling, primarily line transect and point transect sampling, has had a relatively short history. The earliest attempts to use distances to detected animals to estimate abundance date back to the 1930s, and the first line transect estimator with a rigorous mathematical basis was due to Hayne (1949). Nearly 20 years later, Gates et al. (1968) and Eberhardt (1968) made important contributions to the development of line transect sampling methodology. Neither the radial distance model of Hayne (1949) nor the negative exponential model of Gates et al. (1968) is based on plausible assumptions about the detection process. Eberhardt’s (1968) work was more conceptual, and attempted to provide a class of models that were robust to differing detection processes.
Cited by 0
Seth Stapleton (595081), Michelle LaRue (595082), Nicolas Lecomte (112254) et al. · Figshare · 2015
<p>Results of distance sampling analyses of a polar bear aerial survey conducted in northern Foxe Basin, Nunavut, Canada during August – September, 2012. Highly supported models (ΔAIC<i><sub>c</sub></i><3) are presented. In the column Model, the key function is followed by adjustment terms or covariates (VIS = visibility; poor/fair (e.g., glare, light fog or rain) or excellent; LIGHT = light conditions; overcast, mostly cloudy, or partly cloudy/clear). ESW = Effective strip width (meters). p = Detection probability. = Abundance estimate. Goodness of Fit metrics: C-S = Chi-squared; K-S = Kolmogorov-Smirnov; C-vM = Cramér-von Mises.</p>
Cited by 0Open access
Tiago A. Marques · Significance · 2009
Abstract All too often we hear in the news statements like “there are, at most, a few hundred individuals left of this endangered species” or “there is small hope for the persistence of this population given that so few are left”. How do scientists count animals to make such statements?Tiago Marques explains the concepts and pitfalls of distance sampling—one of the most widely used methods for estimating animal populations.
Cited by 3Open access