Estimation of larval feeding rates using normal linear models involving censored and truncated observations

Abstract

Experiments to estimate the feeding rates of aquatic insect larvae involved destructive sampling of larvae to determine the position of an introduced food marker as it passed through their guts. A normal linear model involving censoring (equal to complete passage) and truncation is fitted to the measurement of the passage of food. A method for maximum likelihood estimation is derived together with the second order variance-covariance equations. Methods for estimating the effect of larval size on feeding rate are examined.