The article discusses the application and methodology of Positive Mathematical Programming (PMP) in agricultural economics. PMP is a method for constructing flexible models of agricultural production and resource use that are consistent with microeconomic theory and prior estimates of demand and supply elasticities. Unlike traditional linear programming models, PMP uses a minimal data set in a more flexible manner, allowing for self-calibrating models that respond smoothly to changes in parameters. The paper highlights the importance of calibration in programming models, particularly in ensuring that models accurately reflect real-world production patterns and are consistent with empirical data. PMP is particularly useful in agricultural economic policy analysis, where models are often constrained by limited data and structural changes in economies. The method allows for the calibration of models without the need for "flexibility" constraints, leading to more accurate and responsive models. The paper also addresses calibration problems in programming models, such as the challenge of ensuring that models accurately reflect observed production patterns and the need to account for the effects of policy changes on resource allocation. The article presents a detailed methodology for calibrating PMP models, including the use of dual values from the first stage of the calibration process to derive quadratic cost functions. It also discusses the use of elasticity priors in extending PMP models to incorporate supply and demand elasticities, which can help in bounding the results of the calibration process. The paper concludes with a discussion of the practical implementation of PMP, emphasizing its ability to produce self-calibrating models that are consistent with empirical data and can be used for policy analysis. The methodology is illustrated with a simple example involving two crops and one allocatable input, demonstrating how PMP can be applied to agricultural production models.The article discusses the application and methodology of Positive Mathematical Programming (PMP) in agricultural economics. PMP is a method for constructing flexible models of agricultural production and resource use that are consistent with microeconomic theory and prior estimates of demand and supply elasticities. Unlike traditional linear programming models, PMP uses a minimal data set in a more flexible manner, allowing for self-calibrating models that respond smoothly to changes in parameters. The paper highlights the importance of calibration in programming models, particularly in ensuring that models accurately reflect real-world production patterns and are consistent with empirical data. PMP is particularly useful in agricultural economic policy analysis, where models are often constrained by limited data and structural changes in economies. The method allows for the calibration of models without the need for "flexibility" constraints, leading to more accurate and responsive models. The paper also addresses calibration problems in programming models, such as the challenge of ensuring that models accurately reflect observed production patterns and the need to account for the effects of policy changes on resource allocation. The article presents a detailed methodology for calibrating PMP models, including the use of dual values from the first stage of the calibration process to derive quadratic cost functions. It also discusses the use of elasticity priors in extending PMP models to incorporate supply and demand elasticities, which can help in bounding the results of the calibration process. The paper concludes with a discussion of the practical implementation of PMP, emphasizing its ability to produce self-calibrating models that are consistent with empirical data and can be used for policy analysis. The methodology is illustrated with a simple example involving two crops and one allocatable input, demonstrating how PMP can be applied to agricultural production models.