Semiparametric Estimation of Animal Abundance Using Capture–Recapture Data from Open Populations

Huggins, Richard

doi:10.1111/j.1541-0420.2005.00508.x

“…Note that j are martingale differences and hence are uncorrelated. As in [6], from the properties of the hypergeometric distribution, we have that Var (m j | N j , n j , M j ) j (M j /N j )(1 − M j /N j )(N j − n j )/(N j − 1). Hence,…”

Section: Discussionmentioning

confidence: 97%

“…It was noted in [6] that the covariance terms are negative so that ignoring them produces a conservative estimate of the variance. Then, we propose an approximate estimate of the covariance matrix of β as…”

Section: Discussionmentioning

confidence: 98%

“…The model allows for additional time-varying covariates, which may be modelled both parametrically and nonparametrically, and for parametric effects such as seasonal effects. By fixing a large number of knots and making a prior selection of penalty orders, we used a version of GCV to choose a global bandwidth rather than the local bandwidth of the kernel smoothing approach of Huggins [6]. This approach is still much faster computationally than local polynomial kernel methods, allowing for larger data sets (more capture occasions) and additional covariates to be included in the analysis.…”

Section: Discussionmentioning

confidence: 99%

“…To illustrate our approach, we consider capture data on the Little Penguin, Eudyptula minor, that are the same as those analysed in [6,8]. These data were collected by the Penguin Study Group at approximately monthly intervals from July 1990 to May 1995 at the Phillip Island Nature Parks at Summerland Beach on the western end of Phillip Island, Victoria, Australia.…”

Section: Introductionmentioning

confidence: 99%

“…The estimators of Huggins and Yip [3] were nonparametric and there was no allowance for the effect of covariates on the estimators. Huggins [6] introduced partially linear models for the population size that allow the inclusion of covariates in the model to explain seasonal effects, for example. In these models, the population size is estimated as a function of time.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Semiparametric inference for open populations using the Jolly–Seber model: a penalized spline approach

Huggins

¹

,

Stoklosa

²

2013

Journal of Statistical Computation and Simulation

Self Cite

View full text Add to dashboard Cite

When there are frequent capture occasions, both semiparametric and nonparametric estimators for the size of an open population have been proposed using kernel smoothing methods. While kernel smoothing methods are mathematically tractable, fitting them to data is computationally intensive. Here, we use smoothing splines in the form of P-splines to provide an alternate less computationally intensive method of fitting these models to capture-recapture data from open populations with frequent capture occasions. We fit the model to capture data collected over 64 occasions and model the population size as a function of time, seasonal effects and an environmental covariate. A small simulation study is also conducted to examine the performance of the estimators and their standard errors.

show abstract

Capture‐Recapture Methodology

Gould

¹

,

Kendall

²

2012

Encyclopedia of Environmetrics

View full text Add to dashboard Cite

Capture‐recapture methods were initially developed to estimate human population abundance, but since that time have seen widespread use for fish and wildlife populations to estimate and model various parameters of population, metapopulation, and disease dynamics. Repeated sampling of marked animals provides information for estimating abundance and tracking the fate of individuals in the face of imperfect detection. Mark types have evolved from clipping or tagging to use of noninvasive methods such as photography of natural markings and DNA collection from feces. Survival estimation has been emphasized more recently as have transition probabilities between life history states and/or geographical locations, even where some states are unobservable or uncertain. Sophisticated software has been developed to handle highly parameterized models, including environmental and individual covariates, to conduct model selection, and to employ various estimation approaches such as maximum likelihood and Bayesian approaches. With these user‐friendly tools, complex statistical models for studying population dynamics have been made available to ecologists. The future will include a continuing trend toward integrating data types, both for tagged and untagged individuals, to produce more precise and robust population models.

show abstract

Capture‐Recapture Methodology

Gould¹,

Kendall²

2014

Wiley StatsRef: Statistics Reference Online

View full text Add to dashboard Cite

Capture‐recapture methods were initially developed to estimate human population abundance, but since that time have seen widespread use for fish and wildlife populations to estimate and model various parameters of population, metapopulation, and disease dynamics. Repeated sampling of marked animals provides information for estimating abundance and tracking the fate of individuals in the face of imperfect detection. Mark types have evolved from clipping or tagging to use of noninvasive methods such as photography of natural markings and DNA collection from feces. Survival estimation has been emphasized more recently as have transition probabilities between life history states and/or geographical locations, even where some states are unobservable or uncertain. Sophisticated software has been developed to handle highly parameterized models, including environmental and individual covariates, to conduct model selection, and to employ various estimation approaches such as maximum likelihood and Bayesian approaches. With these user‐friendly tools, complex statistical models for studying population dynamics have been made available to ecologists. The future will include a continuing trend toward integrating data types, both for tagged and untagged individuals, to produce more precise and robust population models.

show abstract

Semiparametric Estimation of Animal Abundance Using Capture–Recapture Data from Open Populations

Cited by 7 publications

References 15 publications

Semiparametric inference for open populations using the Jolly–Seber model: a penalized spline approach

Semiparametric inference for open populations using the Jolly–Seber model: a penalized spline approach

Capture‐Recapture Methodology

Capture‐Recapture Methodology

Contact Info

Product

Resources

About