SIMULTANEOUS-EQUATIONS BIAS OF ANIMAL PRODUCTION SYSTEMS

The problem of simultaneous equations and their ensuing bias when examining animal production is the result of either: (1) true biological interactions; (2) aggregated observation periods; or/and (3) the fact that in multiple-output production processes, economic theory of production predicts a simultaneous determination of the optimum output levels. The simultaneous-equations bias should be considered if the conceptual analysis of the biological system suggests the presence of the bias. A standard linear model (such as the ordinary least-squares regression model) which ignores this simultaneity might produce biased and inconsistent regression coefficients. In the present study of milk production, the different estimates and significance levels of the regression coefficients of a simultaneous-equations model compared with an ordinary least-squares regression model indicated the presence of simultaneous-equations bias. A practical consequence of ignoring this bias is the flawed estimation of herd health benefits, e.g. seven times larger benefits from improved reproduction were indicated if the simultaneous-equations bias was accounted for. The population studied was the 1913 dairy herds participating in the Norwegian farm efficiency program during 1987.