Some comments on line transect grouped data analysis

Anderson and Pospahala (1970, J. Wildl. Manag. 34, 141–146) investigated the estimation of wildlife population size or abundance using the belt or line transect sampling method and devised a correction for bias, thus leading to an estimator with interesting statistical characteristics. This work was given a more uniform mathematical framework in Burnham and Anderson (1976, Biometrics 32, 325–336). In this paper we investigate several ways to generalize that correction for bias, and suggest that the data analyst has available a number of alternative directions that can, and indeed should, be explored.