This paper examines recent literature on the identification of production functions, focusing on structural techniques from Olley and Pakes (1996) and Levinsohn and Petrin (2003). While these papers offer intuitive identification ideas, the authors argue that the techniques, particularly those of Levinsohn and Petrin, suffer from collinearity problems that cast doubt on their methodology. They suggest alternative methodologies that use ideas from these papers but avoid these collinearity issues. Production functions relate inputs to outputs and face endogeneity problems due to unobserved factors affecting production. Two early solutions to this problem are instrumental variables (IV) and fixed-effects estimation. However, these methods have not been particularly successful. Recent techniques, including dynamic panel data methods and structural approaches, have been introduced to address these issues. The structural approaches of Olley and Pakes (OP) and Levinsohn and Petrin (LP) use observed input decisions to control for unobserved productivity shocks. These methods have been applied in various empirical studies. However, the authors argue that the LP approach suffers from collinearity problems, making it difficult to identify parameters. They propose an alternative estimation approach that avoids these issues by using investment or intermediate inputs to proxy for productivity shocks. This approach is more stable and allows for comparison with dynamic panel data methods, helping empirical researchers choose between different approaches. The authors also show that their estimator performs better in practice compared to the LP methodology.This paper examines recent literature on the identification of production functions, focusing on structural techniques from Olley and Pakes (1996) and Levinsohn and Petrin (2003). While these papers offer intuitive identification ideas, the authors argue that the techniques, particularly those of Levinsohn and Petrin, suffer from collinearity problems that cast doubt on their methodology. They suggest alternative methodologies that use ideas from these papers but avoid these collinearity issues. Production functions relate inputs to outputs and face endogeneity problems due to unobserved factors affecting production. Two early solutions to this problem are instrumental variables (IV) and fixed-effects estimation. However, these methods have not been particularly successful. Recent techniques, including dynamic panel data methods and structural approaches, have been introduced to address these issues. The structural approaches of Olley and Pakes (OP) and Levinsohn and Petrin (LP) use observed input decisions to control for unobserved productivity shocks. These methods have been applied in various empirical studies. However, the authors argue that the LP approach suffers from collinearity problems, making it difficult to identify parameters. They propose an alternative estimation approach that avoids these issues by using investment or intermediate inputs to proxy for productivity shocks. This approach is more stable and allows for comparison with dynamic panel data methods, helping empirical researchers choose between different approaches. The authors also show that their estimator performs better in practice compared to the LP methodology.