Skip to content

Research at St Andrews

Distance sampling with a random scale detection function

Research output: Contribution to journalArticle

Standard

Distance sampling with a random scale detection function. / Oedekoven, C.S.; Laake, J.L.; Skaug, H.J.

In: Environmental and Ecological Statistics, Vol. 22, No. 4, 12.2015, p. 725-737.

Research output: Contribution to journalArticle

Harvard

Oedekoven, CS, Laake, JL & Skaug, HJ 2015, 'Distance sampling with a random scale detection function', Environmental and Ecological Statistics, vol. 22, no. 4, pp. 725-737. https://doi.org/10.1007/s10651-015-0316-9

APA

Oedekoven, C. S., Laake, J. L., & Skaug, H. J. (2015). Distance sampling with a random scale detection function. Environmental and Ecological Statistics, 22(4), 725-737. https://doi.org/10.1007/s10651-015-0316-9

Vancouver

Oedekoven CS, Laake JL, Skaug HJ. Distance sampling with a random scale detection function. Environmental and Ecological Statistics. 2015 Dec;22(4):725-737. https://doi.org/10.1007/s10651-015-0316-9

Author

Oedekoven, C.S. ; Laake, J.L. ; Skaug, H.J. / Distance sampling with a random scale detection function. In: Environmental and Ecological Statistics. 2015 ; Vol. 22, No. 4. pp. 725-737.

Bibtex - Download

@article{24b1107a38ce4c44b79c8f58192d327d,
title = "Distance sampling with a random scale detection function",
abstract = "Distance sampling was developed to estimate wildlife abundance from observational surveys with uncertain detection in the search area. We present novel analysis methods for estimating detection probabilities that make use of random effects models to allow for unmodeled heterogeneity in detection. The scale parameter of the half-normal detection function is modeled by means of an intercept plus an error term varying with detections, normally distributed with zero mean and unknown variance. In contrast to conventional distance sampling methods, our approach can deal with long-tailed detection functions without truncation. Compared to a fixed effect covariate approach, we think of the random effect as a covariate with unknown values and integrate over the random effect. We expand the random scale to a mixed scale model by adding fixed effect covariates. We analyzed simulated data with large sample sizes to demonstrate that the code performs correctly for random and mixed effect models. We also generated replicate simulations with more practical sample sizes ((Formula presented.)) and compared the random scale half-normal with the hazard rate detection function. As expected each estimation model was best for different simulation models. We illustrate the mixed effect modeling approach using harbor porpoise vessel survey data where the mixed effect model provided an improved model fit in comparison to a fixed effect model with the same covariates. We propose that a random or mixed effect model of the detection function scale be adopted as one of the standard approaches for fitting detection functions in distance sampling.",
keywords = "Abundance estimation, AD Model Builder, Half-normal, Harbor porpoise detections, Heterogeneity in detection probabilities, Mixed effects",
author = "C.S. Oedekoven and J.L. Laake and H.J. Skaug",
note = "Cornelia Oedekoven was supported by a studentship jointly funded by the University of St Andrews and EP-SRC, through the National Centre for Statistical Ecology (EP-SRC Grant EP/C522702/1). Hans Skaug thanks the Center for Stock Assessment Research for facilitating his visit to University of California, Santa Cruz.",
year = "2015",
month = "12",
doi = "10.1007/s10651-015-0316-9",
language = "English",
volume = "22",
pages = "725--737",
journal = "Environmental and Ecological Statistics",
issn = "1352-8505",
publisher = "Springer",
number = "4",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Distance sampling with a random scale detection function

AU - Oedekoven, C.S.

AU - Laake, J.L.

AU - Skaug, H.J.

N1 - Cornelia Oedekoven was supported by a studentship jointly funded by the University of St Andrews and EP-SRC, through the National Centre for Statistical Ecology (EP-SRC Grant EP/C522702/1). Hans Skaug thanks the Center for Stock Assessment Research for facilitating his visit to University of California, Santa Cruz.

PY - 2015/12

Y1 - 2015/12

N2 - Distance sampling was developed to estimate wildlife abundance from observational surveys with uncertain detection in the search area. We present novel analysis methods for estimating detection probabilities that make use of random effects models to allow for unmodeled heterogeneity in detection. The scale parameter of the half-normal detection function is modeled by means of an intercept plus an error term varying with detections, normally distributed with zero mean and unknown variance. In contrast to conventional distance sampling methods, our approach can deal with long-tailed detection functions without truncation. Compared to a fixed effect covariate approach, we think of the random effect as a covariate with unknown values and integrate over the random effect. We expand the random scale to a mixed scale model by adding fixed effect covariates. We analyzed simulated data with large sample sizes to demonstrate that the code performs correctly for random and mixed effect models. We also generated replicate simulations with more practical sample sizes ((Formula presented.)) and compared the random scale half-normal with the hazard rate detection function. As expected each estimation model was best for different simulation models. We illustrate the mixed effect modeling approach using harbor porpoise vessel survey data where the mixed effect model provided an improved model fit in comparison to a fixed effect model with the same covariates. We propose that a random or mixed effect model of the detection function scale be adopted as one of the standard approaches for fitting detection functions in distance sampling.

AB - Distance sampling was developed to estimate wildlife abundance from observational surveys with uncertain detection in the search area. We present novel analysis methods for estimating detection probabilities that make use of random effects models to allow for unmodeled heterogeneity in detection. The scale parameter of the half-normal detection function is modeled by means of an intercept plus an error term varying with detections, normally distributed with zero mean and unknown variance. In contrast to conventional distance sampling methods, our approach can deal with long-tailed detection functions without truncation. Compared to a fixed effect covariate approach, we think of the random effect as a covariate with unknown values and integrate over the random effect. We expand the random scale to a mixed scale model by adding fixed effect covariates. We analyzed simulated data with large sample sizes to demonstrate that the code performs correctly for random and mixed effect models. We also generated replicate simulations with more practical sample sizes ((Formula presented.)) and compared the random scale half-normal with the hazard rate detection function. As expected each estimation model was best for different simulation models. We illustrate the mixed effect modeling approach using harbor porpoise vessel survey data where the mixed effect model provided an improved model fit in comparison to a fixed effect model with the same covariates. We propose that a random or mixed effect model of the detection function scale be adopted as one of the standard approaches for fitting detection functions in distance sampling.

KW - Abundance estimation

KW - AD Model Builder

KW - Half-normal

KW - Harbor porpoise detections

KW - Heterogeneity in detection probabilities

KW - Mixed effects

UR - http://static-content.springer.com/esm/art%3A10.1007%2Fs10651-015-0316-9/MediaObjects/10651_2015_316_MOESM1_ESM.pdf

U2 - 10.1007/s10651-015-0316-9

DO - 10.1007/s10651-015-0316-9

M3 - Article

VL - 22

SP - 725

EP - 737

JO - Environmental and Ecological Statistics

JF - Environmental and Ecological Statistics

SN - 1352-8505

IS - 4

ER -

Related by author

  1. Accuracy and precision of dolphin group size estimates

    Gerrodette, T., Perryman, W. L. & Oedekoven, C. S., Jan 2019, In : Marine Mammal Science. 35, 1, p. 22-39 18 p.

    Research output: Contribution to journalArticle

  2. Attributing changes in the distribution of species abundance to weather variables using the example of British breeding birds

    Oedekoven, C. S., Elston, D. A., Harrison, P. J., Brewer, M. J., Buckland, S. T., Johnston, A., Foster, S. & Pearce-Higgins, J. W., Dec 2017, In : Methods in Ecology and Evolution. 8, 12, p. 1690-1702

    Research output: Contribution to journalArticle

  3. Sperm whale (Physeter macrocephalus) collision with a research vessel: accidental collision or deliberate ramming?

    Fulling, G. L., Jefferson, T. A., Fertl, D., Salinas Vega, J. C., Oedekoven, C. S. & Kuczaj II, S. A., 10 Jul 2017, In : Aquatic Mammals. 43, 4, p. 421-429

    Research output: Contribution to journalArticle

  4. Low tortoise abundances in pine forest plantations in forest-shrubland transition areas

    Rodríguez-Caro, R. C., Oedekoven, C. S., Graciá, E., Anadón, J. D., Buckland, S. T., Esteve-Selma, M. A., Martinez, J. & Giménez, A., 8 Mar 2017, In : PLoS One. 12, 3, 13 p., e0173485.

    Research output: Contribution to journalArticle

  5. From physiology to policy: a review of physiological noise effects on marine fauna with implications for mitigation

    Aguilar De Soto, N., Gkikopoulou, K., Hooker, S., Isojunno, S., Johnson, M., Miller, P., Tyack, P., Wensveen, P., Donovan, C., Harris, C. M., Harris, D., Marshall, L., Oedekoven, C., Prieto, R. & Thomas, L., Dec 2016, In : Proceedings of Meetings on Acoustics. 27, 1, 14 p., 040008.

    Research output: Contribution to journalReview article

Related by journal

  1. Environmental and Ecological Statistics (Journal)

    Stephen Terrence Buckland (Member of editorial board)
    20042008

    Activity: Publication peer-review and editorial work typesEditor of research journal

Related by journal

  1. Estimation bias under model selection for distance sampling detection functions

    Prieto Gonzalez, R., Thomas, L. & Marques, T. A., Sep 2017, In : Environmental and Ecological Statistics. 24, 3, p. 399-414 16 p.

    Research output: Contribution to journalArticle

  2. Imperfect observations in ecological studies

    Shimadzu, H., Foster, S. D. & Darnell, R., Sep 2016, In : Environmental and Ecological Statistics. 23, 3, p. 337-358 22 p.

    Research output: Contribution to journalArticle

  3. Finite area smoothing with generalized distance splines

    Miller, D. L. & Wood, S. N., 2014, In : Environmental and Ecological Statistics. 21, 4, p. 715-731 17 p.

    Research output: Contribution to journalArticle

  4. A family of spatial biodiversity measures based on graphs

    Rajala, T. & Illian, J. B., Dec 2012, In : Environmental and Ecological Statistics. 19, 4, p. 545-572 28 p.

    Research output: Contribution to journalArticle

ID: 180107219

Top