Estimation of individual growth trajectories when repeated measures are missing

Research output: Contribution to journalJournal article – Annual report year: 2017Researchpeer-review

Standard

Estimation of individual growth trajectories when repeated measures are missing. / Brooks, Mollie Elizabeth; Clements, Christopher; Pemberton, Josephine; Ozgul, Arpat.

In: American Naturalist, Vol. 190, No. 3, 2017, p. 377-388.

Research output: Contribution to journalJournal article – Annual report year: 2017Researchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Brooks, Mollie Elizabeth ; Clements, Christopher ; Pemberton, Josephine ; Ozgul, Arpat. / Estimation of individual growth trajectories when repeated measures are missing. In: American Naturalist. 2017 ; Vol. 190, No. 3. pp. 377-388.

Bibtex

@article{b88d81ba2df346109c6e96b9ab4f3bee,
title = "Estimation of individual growth trajectories when repeated measures are missing",
abstract = "Individuals in a population vary in their growth due to hidden and observed factors such as age, genetics, environment, disease, and carryover effects from past environments. Because size affects fitness, growth trajectories scale up to affect population dynamics. However, it can be difficult to estimate growth in data from wild populations with missing observations and observation error. Previous work has shown that linear mixed models (LMMs) underestimate hidden individual heterogeneity when more than 25{\%} of repeated measures are missing. Here we demonstrate a flexible and robust way to model growth trajectories. We show that state-space models (SSMs), fit using R package growmod, are far less biased than LMMs when fit to simulated data sets with missing repeated measures and observation error. This method is much faster than Markov chain Monte Carlo methods, allowing more models to be tested in a shorter time. For the scenarios we simulated, SSMs gave estimates with little bias when up to 87.5{\%} of repeated measures were missing. We use this method to quantify growth of Soay sheep, using data from a long-term mark-recapture study, and demonstrate that growth decreased with age, population density, weather conditions, and when individuals are reproductive. The method improves our ability to quantify how growth varies among individuals in response to their attributes and the environments they experience, with particular relevance for wild populations.",
keywords = "Soay sheep, Template Model Builder, individual quality, reproductive costs, state-space model, time series",
author = "Brooks, {Mollie Elizabeth} and Christopher Clements and Josephine Pemberton and Arpat Ozgul",
year = "2017",
doi = "10.1086/692797",
language = "English",
volume = "190",
pages = "377--388",
journal = "American Naturalist",
issn = "0003-0147",
publisher = "University of Chicago Press",
number = "3",

}

RIS

TY - JOUR

T1 - Estimation of individual growth trajectories when repeated measures are missing

AU - Brooks, Mollie Elizabeth

AU - Clements, Christopher

AU - Pemberton, Josephine

AU - Ozgul, Arpat

PY - 2017

Y1 - 2017

N2 - Individuals in a population vary in their growth due to hidden and observed factors such as age, genetics, environment, disease, and carryover effects from past environments. Because size affects fitness, growth trajectories scale up to affect population dynamics. However, it can be difficult to estimate growth in data from wild populations with missing observations and observation error. Previous work has shown that linear mixed models (LMMs) underestimate hidden individual heterogeneity when more than 25% of repeated measures are missing. Here we demonstrate a flexible and robust way to model growth trajectories. We show that state-space models (SSMs), fit using R package growmod, are far less biased than LMMs when fit to simulated data sets with missing repeated measures and observation error. This method is much faster than Markov chain Monte Carlo methods, allowing more models to be tested in a shorter time. For the scenarios we simulated, SSMs gave estimates with little bias when up to 87.5% of repeated measures were missing. We use this method to quantify growth of Soay sheep, using data from a long-term mark-recapture study, and demonstrate that growth decreased with age, population density, weather conditions, and when individuals are reproductive. The method improves our ability to quantify how growth varies among individuals in response to their attributes and the environments they experience, with particular relevance for wild populations.

AB - Individuals in a population vary in their growth due to hidden and observed factors such as age, genetics, environment, disease, and carryover effects from past environments. Because size affects fitness, growth trajectories scale up to affect population dynamics. However, it can be difficult to estimate growth in data from wild populations with missing observations and observation error. Previous work has shown that linear mixed models (LMMs) underestimate hidden individual heterogeneity when more than 25% of repeated measures are missing. Here we demonstrate a flexible and robust way to model growth trajectories. We show that state-space models (SSMs), fit using R package growmod, are far less biased than LMMs when fit to simulated data sets with missing repeated measures and observation error. This method is much faster than Markov chain Monte Carlo methods, allowing more models to be tested in a shorter time. For the scenarios we simulated, SSMs gave estimates with little bias when up to 87.5% of repeated measures were missing. We use this method to quantify growth of Soay sheep, using data from a long-term mark-recapture study, and demonstrate that growth decreased with age, population density, weather conditions, and when individuals are reproductive. The method improves our ability to quantify how growth varies among individuals in response to their attributes and the environments they experience, with particular relevance for wild populations.

KW - Soay sheep

KW - Template Model Builder

KW - individual quality

KW - reproductive costs

KW - state-space model

KW - time series

U2 - 10.1086/692797

DO - 10.1086/692797

M3 - Journal article

VL - 190

SP - 377

EP - 388

JO - American Naturalist

JF - American Naturalist

SN - 0003-0147

IS - 3

ER -