Finding the smoothest path to success

Model complexity and the consideration of nonlinear patterns in nest-survival data

Max Post Van Der Burg, Larkin A. Powell, Richard AJ Tyre

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Quantifying patterns of nest survival is a first step toward understanding why birds decide when and where to breed. Most studies of nest survival have relied on generalized linear models (GLM) to explore these patterns. However, GLMs require assumptions about the models' structure that might preclude finding nonlinear patterns in survival data. Generalized additive models (GAM) provide a flexible alternative to GLMs for estimating linear and nonlinear patterns in data. Here we present a comparison of GLMs and GAMs for explaining variation in nest-survival data. We used two different model-selection criteria, the Bayes (BIC) and Akaike (AIC) information criteria, to select among simple and complex models. Our study was focused on the analysis of Red-winged Blackbird (Agelaius phoeniceus) nests in the Rainwater Basin wetlands of south-central Nebraska. Under BIC, our quadratic model of nest age had the most support, and the model predicted a concave pattern of daily nest survival. We found more model-selection uncertainty under AIC and found support for additive models with ordinal effects of both day and age. These models predicted much more temporal variation than did the linear models. Following our analysis, we discuss some of the advantages and disadvantages of GAMs. Despite the possible limitations of GAMs, our results suggest that they provide an efficient and flexible way to demonstrate nonlinear patterns in nest-survival data.

Original languageEnglish (US)
Pages (from-to)421-431
Number of pages11
JournalCondor
Volume112
Issue number3
DOIs
StatePublished - Aug 1 2010

Fingerprint

nest
nests
Agelaius phoeniceus
linear models
selection criteria
Akaike information criterion
temporal variation
rainwater
wetlands
uncertainty
basins
breeds
rain
wetland
birds
bird
basin

Keywords

  • Daily nest survival
  • Generalized additive models (GAM)
  • Generalized linear models (GLM)
  • Logistic exposure

ASJC Scopus subject areas

  • Ecology, Evolution, Behavior and Systematics
  • Animal Science and Zoology

Cite this

Finding the smoothest path to success : Model complexity and the consideration of nonlinear patterns in nest-survival data. / Van Der Burg, Max Post; Powell, Larkin A.; Tyre, Richard AJ.

In: Condor, Vol. 112, No. 3, 01.08.2010, p. 421-431.

Research output: Contribution to journalArticle

@article{33816660742c49c9b86ccf4ebe1cae3b,
title = "Finding the smoothest path to success: Model complexity and the consideration of nonlinear patterns in nest-survival data",
abstract = "Quantifying patterns of nest survival is a first step toward understanding why birds decide when and where to breed. Most studies of nest survival have relied on generalized linear models (GLM) to explore these patterns. However, GLMs require assumptions about the models' structure that might preclude finding nonlinear patterns in survival data. Generalized additive models (GAM) provide a flexible alternative to GLMs for estimating linear and nonlinear patterns in data. Here we present a comparison of GLMs and GAMs for explaining variation in nest-survival data. We used two different model-selection criteria, the Bayes (BIC) and Akaike (AIC) information criteria, to select among simple and complex models. Our study was focused on the analysis of Red-winged Blackbird (Agelaius phoeniceus) nests in the Rainwater Basin wetlands of south-central Nebraska. Under BIC, our quadratic model of nest age had the most support, and the model predicted a concave pattern of daily nest survival. We found more model-selection uncertainty under AIC and found support for additive models with ordinal effects of both day and age. These models predicted much more temporal variation than did the linear models. Following our analysis, we discuss some of the advantages and disadvantages of GAMs. Despite the possible limitations of GAMs, our results suggest that they provide an efficient and flexible way to demonstrate nonlinear patterns in nest-survival data.",
keywords = "Daily nest survival, Generalized additive models (GAM), Generalized linear models (GLM), Logistic exposure",
author = "{Van Der Burg}, {Max Post} and Powell, {Larkin A.} and Tyre, {Richard AJ}",
year = "2010",
month = "8",
day = "1",
doi = "10.1525/cond.2010.090053",
language = "English (US)",
volume = "112",
pages = "421--431",
journal = "Condor",
issn = "0010-5422",
publisher = "American Ornithologist Society",
number = "3",

}

TY - JOUR

T1 - Finding the smoothest path to success

T2 - Model complexity and the consideration of nonlinear patterns in nest-survival data

AU - Van Der Burg, Max Post

AU - Powell, Larkin A.

AU - Tyre, Richard AJ

PY - 2010/8/1

Y1 - 2010/8/1

N2 - Quantifying patterns of nest survival is a first step toward understanding why birds decide when and where to breed. Most studies of nest survival have relied on generalized linear models (GLM) to explore these patterns. However, GLMs require assumptions about the models' structure that might preclude finding nonlinear patterns in survival data. Generalized additive models (GAM) provide a flexible alternative to GLMs for estimating linear and nonlinear patterns in data. Here we present a comparison of GLMs and GAMs for explaining variation in nest-survival data. We used two different model-selection criteria, the Bayes (BIC) and Akaike (AIC) information criteria, to select among simple and complex models. Our study was focused on the analysis of Red-winged Blackbird (Agelaius phoeniceus) nests in the Rainwater Basin wetlands of south-central Nebraska. Under BIC, our quadratic model of nest age had the most support, and the model predicted a concave pattern of daily nest survival. We found more model-selection uncertainty under AIC and found support for additive models with ordinal effects of both day and age. These models predicted much more temporal variation than did the linear models. Following our analysis, we discuss some of the advantages and disadvantages of GAMs. Despite the possible limitations of GAMs, our results suggest that they provide an efficient and flexible way to demonstrate nonlinear patterns in nest-survival data.

AB - Quantifying patterns of nest survival is a first step toward understanding why birds decide when and where to breed. Most studies of nest survival have relied on generalized linear models (GLM) to explore these patterns. However, GLMs require assumptions about the models' structure that might preclude finding nonlinear patterns in survival data. Generalized additive models (GAM) provide a flexible alternative to GLMs for estimating linear and nonlinear patterns in data. Here we present a comparison of GLMs and GAMs for explaining variation in nest-survival data. We used two different model-selection criteria, the Bayes (BIC) and Akaike (AIC) information criteria, to select among simple and complex models. Our study was focused on the analysis of Red-winged Blackbird (Agelaius phoeniceus) nests in the Rainwater Basin wetlands of south-central Nebraska. Under BIC, our quadratic model of nest age had the most support, and the model predicted a concave pattern of daily nest survival. We found more model-selection uncertainty under AIC and found support for additive models with ordinal effects of both day and age. These models predicted much more temporal variation than did the linear models. Following our analysis, we discuss some of the advantages and disadvantages of GAMs. Despite the possible limitations of GAMs, our results suggest that they provide an efficient and flexible way to demonstrate nonlinear patterns in nest-survival data.

KW - Daily nest survival

KW - Generalized additive models (GAM)

KW - Generalized linear models (GLM)

KW - Logistic exposure

UR - http://www.scopus.com/inward/record.url?scp=77956932485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956932485&partnerID=8YFLogxK

U2 - 10.1525/cond.2010.090053

DO - 10.1525/cond.2010.090053

M3 - Article

VL - 112

SP - 421

EP - 431

JO - Condor

JF - Condor

SN - 0010-5422

IS - 3

ER -