Detecting variability in demographic rates

Randomization with the Kullback-Leibler distance

Karim Al-Khafaji, Shripad Tuljapurkar, Carol C Horvitz, Anthony Koop

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

1. Environmental stochasticity can play a major role in population dynamics with consequences for population viability and the evolution of life-history traits. However, in empirical studies it is necessary to verify that environmental stochasticity is actually present and that the observed variability is not simply a consequence of sampling variation. 2. We propose a non-parametric method to detect environmental variability in demographic parameters of structured populations based on data randomization using an estimated Kullback-Leibler distance as a test statistic. 3. The Kullback-Leibler distance is an established information-theoretic measure of the deviance between distributions and we show, with empirical and simulated data sets, that it can be adapted effectively to detect variability in demographic fates among populations. 4. This metric has the potential to reveal the importance of relatively rare transitions for understanding temporal variability in demography that would not be revealed by log-linear analysis. 5. Synthesis: Using an estimated Kullback-Leibler distance as a test statistic allows variability at the level of demographic rates to be economically assessed as an adjunct to the randomization tests that many researchers currently perform to assess variability in λ, and would provide additional and complementary insight.

Original languageEnglish
Pages (from-to)1370-1380
Number of pages11
JournalJournal of Ecology
Volume95
Issue number6
DOIs
StatePublished - Nov 1 2007

Fingerprint

demographic statistics
stochasticity
life history trait
demography
population dynamics
viability
statistics
testing
sampling
rate
test
researchers
life history
synthesis
distribution
method
parameter
analysis
methodology

Keywords

  • Demographic census
  • Environmental stochasticity
  • Kullback-Leibler
  • Matrix models
  • Randomization tests

ASJC Scopus subject areas

  • Ecology

Cite this

Detecting variability in demographic rates : Randomization with the Kullback-Leibler distance. / Al-Khafaji, Karim; Tuljapurkar, Shripad; Horvitz, Carol C; Koop, Anthony.

In: Journal of Ecology, Vol. 95, No. 6, 01.11.2007, p. 1370-1380.

Research output: Contribution to journalArticle

Al-Khafaji, Karim ; Tuljapurkar, Shripad ; Horvitz, Carol C ; Koop, Anthony. / Detecting variability in demographic rates : Randomization with the Kullback-Leibler distance. In: Journal of Ecology. 2007 ; Vol. 95, No. 6. pp. 1370-1380.
@article{9eef63446de7412bb56a1c0a1b0e44b7,
title = "Detecting variability in demographic rates: Randomization with the Kullback-Leibler distance",
abstract = "1. Environmental stochasticity can play a major role in population dynamics with consequences for population viability and the evolution of life-history traits. However, in empirical studies it is necessary to verify that environmental stochasticity is actually present and that the observed variability is not simply a consequence of sampling variation. 2. We propose a non-parametric method to detect environmental variability in demographic parameters of structured populations based on data randomization using an estimated Kullback-Leibler distance as a test statistic. 3. The Kullback-Leibler distance is an established information-theoretic measure of the deviance between distributions and we show, with empirical and simulated data sets, that it can be adapted effectively to detect variability in demographic fates among populations. 4. This metric has the potential to reveal the importance of relatively rare transitions for understanding temporal variability in demography that would not be revealed by log-linear analysis. 5. Synthesis: Using an estimated Kullback-Leibler distance as a test statistic allows variability at the level of demographic rates to be economically assessed as an adjunct to the randomization tests that many researchers currently perform to assess variability in λ, and would provide additional and complementary insight.",
keywords = "Demographic census, Environmental stochasticity, Kullback-Leibler, Matrix models, Randomization tests",
author = "Karim Al-Khafaji and Shripad Tuljapurkar and Horvitz, {Carol C} and Anthony Koop",
year = "2007",
month = "11",
day = "1",
doi = "10.1111/j.1365-2745.2007.01296.x",
language = "English",
volume = "95",
pages = "1370--1380",
journal = "Journal of Ecology",
issn = "0022-0477",
publisher = "Wiley-Blackwell",
number = "6",

}

TY - JOUR

T1 - Detecting variability in demographic rates

T2 - Randomization with the Kullback-Leibler distance

AU - Al-Khafaji, Karim

AU - Tuljapurkar, Shripad

AU - Horvitz, Carol C

AU - Koop, Anthony

PY - 2007/11/1

Y1 - 2007/11/1

N2 - 1. Environmental stochasticity can play a major role in population dynamics with consequences for population viability and the evolution of life-history traits. However, in empirical studies it is necessary to verify that environmental stochasticity is actually present and that the observed variability is not simply a consequence of sampling variation. 2. We propose a non-parametric method to detect environmental variability in demographic parameters of structured populations based on data randomization using an estimated Kullback-Leibler distance as a test statistic. 3. The Kullback-Leibler distance is an established information-theoretic measure of the deviance between distributions and we show, with empirical and simulated data sets, that it can be adapted effectively to detect variability in demographic fates among populations. 4. This metric has the potential to reveal the importance of relatively rare transitions for understanding temporal variability in demography that would not be revealed by log-linear analysis. 5. Synthesis: Using an estimated Kullback-Leibler distance as a test statistic allows variability at the level of demographic rates to be economically assessed as an adjunct to the randomization tests that many researchers currently perform to assess variability in λ, and would provide additional and complementary insight.

AB - 1. Environmental stochasticity can play a major role in population dynamics with consequences for population viability and the evolution of life-history traits. However, in empirical studies it is necessary to verify that environmental stochasticity is actually present and that the observed variability is not simply a consequence of sampling variation. 2. We propose a non-parametric method to detect environmental variability in demographic parameters of structured populations based on data randomization using an estimated Kullback-Leibler distance as a test statistic. 3. The Kullback-Leibler distance is an established information-theoretic measure of the deviance between distributions and we show, with empirical and simulated data sets, that it can be adapted effectively to detect variability in demographic fates among populations. 4. This metric has the potential to reveal the importance of relatively rare transitions for understanding temporal variability in demography that would not be revealed by log-linear analysis. 5. Synthesis: Using an estimated Kullback-Leibler distance as a test statistic allows variability at the level of demographic rates to be economically assessed as an adjunct to the randomization tests that many researchers currently perform to assess variability in λ, and would provide additional and complementary insight.

KW - Demographic census

KW - Environmental stochasticity

KW - Kullback-Leibler

KW - Matrix models

KW - Randomization tests

UR - http://www.scopus.com/inward/record.url?scp=35448958864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35448958864&partnerID=8YFLogxK

U2 - 10.1111/j.1365-2745.2007.01296.x

DO - 10.1111/j.1365-2745.2007.01296.x

M3 - Article

VL - 95

SP - 1370

EP - 1380

JO - Journal of Ecology

JF - Journal of Ecology

SN - 0022-0477

IS - 6

ER -