A Method for the Statistical Analysis of Time-Energy Budgets

In this paper I outline a method for estimating the sampling variance of estimates of mean daily energy expenditure of free-ranging animals, based on time-energy budgets. This method combines estimated components of variation from laboratory and field observations into a single estimate of the overall sample variance. An approximate confidence region for the mean daily ex- penditure can be constructed as well. I illustrate these methods by applying them to the energy budget of the Golden-winged Sunbird (Nectarinia reichenowi) originally published by Gill and Wolf (1975). The total sample variance of the mean daily energy expenditure, when that expenditure is esti- mated from the time-energy budget approach, is a sum of many terms, including the products of the variances of individual variables, the squared estimates of the mean of individual variables, and the products of the estimated means and covariances among the variables. Thus, the estimated sample variance will usually be large. Any biases in estimation will be propagated throughout the calculations, and errors of staggering magnitude can result. Knowledge of the components of total sampling vari- ance and the sensitivity of these estimates to the various sources of bias should aid field biologists in designing time-energy budget studies so that the maximum possible reliability can be achieved.