Moving beyond the mean: an analysis of faecal corticosterone metabolites shows substantial variability both within and across white-tailed deer populations

Abstract

Glucocorticoid (GC) levels have significant impacts on the health and behaviour of wildlife populations and are involved in many essential body functions including circadian rhythm, stress physiology and metabolism. However, studies of GCs in wildlife often focus on estimating mean hormone levels in populations, or a subset of a population, rather than on assessing the entire distribution of hormone levels within populations. Additionally, explorations of population GC data are limited due to the tradeoff between the number of individuals included in studies and the amount of data per individual that can be collected. In this study, we explore patterns of GC level distributions in three white-tailed deer (Odocoileus virginianus) populations using a non-invasive, opportunistic sampling approach. GC levels were assessed by measuring faecal corticosterone metabolite levels ('fCMs') from deer faecal samples throughout the year. We found both population and seasonal differences in fCMs but observed similarly shaped fCM distributions in all populations. Specifically, all population fCM cumulative distributions were found to be very heavy-tailed. We developed two toy models of acute corticosterone elevation in an effort to recreate the observed heavy-tailed distributions. We found that, in all three populations, cumulative fCM distributions were better described by an assumption of large, periodic spikes in corticosterone levels every few days, as opposed to an assumption of random spikes in corticosterone levels. The analyses presented in this study demonstrate the potential for exploring population-level patterns of GC levels from random, opportunistically sampled data. When taken together with individual-focused studies of GC levels, such analyses can improve our understanding of how individual hormone production scales up to population-level patterns.

Keywords: Abbreviations: fCM, faecal corticosterone metabolite level; Faecal corticosterone; GC, glucocorticoid; HPA, hypothalamic–pituitary–adrenal; glucocorticoid modelling; glucocorticoids; hormone distributions.

Figure 1

(A) Boxplots of faecal corticosterone metabolites (fCMs) in deer populations from Kickapoo (KP: grey, leftmost box), Moraine View (MV: blue, center box) and Walnut Point (WP: red, rightmost box). Note log scale on the y-axis. Statistically significant differences are indicated by stars above the boxes. (B) Solid lines—CCDFs of fCMs in deer populations from KP (black, middlemost line), MV (blue, rightmost line) and WP (red, leftmost line). Note log scale on the x-axis. The y-axis is the probability of any observed sample measurement f being greater than X.

Figure 2

Boxplots of faecal corticosterone metabolites (fCMs) in deer populations from Kickapoo (KP: grey, top plot), Moraine View (MV: blue, middle plot) and Walnut Point (WP: red, bottom plot) per month. Note log scale on the y-axis. Statistically significant differences are indicated by stars above the boxes.

Figure 3

Cumulative distributions of observed faecal corticosterone metabolite (fCM) levels in deer from Kickapoo (KP: black), Moraine View (MV: blue) and Walnut Point (WP: red) by month. Note that the heavy-tailed nature of the cumulative distributions is retained when breaking data down by month, with the caveat that some months have sample sizes too low for interpreting the monthly cdf.

Figure 4

Example curves of GC dynamics (insets) for faecal corticosterone metabolite (fCM) levels given random timing of spikes. Spikes represent elevation of fCM levels, followed by exponential decay of fCM levels. Resulting cumulative distributions are shown given random sampling along the curves of GC dynamics (sampling illustrated via vertical red, dashed lines). GC dynamics and cumulative distributions are shown for three values of model parameter x: x < 1 indicates fCM spike frequency is lower than the rate of fCM decay, x = 1 indicates these rates are equal, and x > 1 indicates fCM spikes are more frequent than the rate of fCM decay.

Figure 5

Example curve of GC dynamics for periodic spikes in fCMs (inset) and the associated cumulative distribution obtained via sampling along the curve of GC dynamics (sampling illustrated via vertical red, dashed lines).

Figure 6

(A) Random GC elevation model fit (dashed lines) to observed cumulative distributions (step functions) of faecal corticosterone metabolite (fCM) levels in deer from Kickapoo (KP: black, middlemost lines), Moraine View (MV: blue, rightmost lines) and Walnut Point (WP: red, leftmost lines) (B) Periodic GC elevation model fit. All periodic models pass a goodness of fit test. The random model is only a good fit for MV.