This paper investigates the conditions under which regression quantiles can be estimated by estimating conditional means. The proposed method allows the use of techniques valid for estimating conditional means while providing insights into how regressors affect the entire conditional distribution. It is not intended to replace the well-established quantile regression estimator but offers an alternative approach for estimating regression quantiles in challenging settings. The method is particularly useful in panel data models with individual effects and models with endogenous explanatory variables. The paper presents an estimator that combines estimates of location and scale functions, both identified by conditional expectations. It also includes a simulation study, two empirical applications, and discusses possible extensions. The approach is computationally efficient and allows for the estimation of regression quantiles without crossing, a crucial property often overlooked in empirical applications. The paper also addresses the incidental parameters problem in panel data models and provides a solution for estimating structural quantile functions in the presence of endogenous regressors. The proposed estimator is compared with existing methods, and its performance is evaluated through simulations and empirical examples. The results show that the estimator performs well, especially when bias-corrected, and is computationally efficient. The paper concludes that the proposed method is a useful tool for estimating regression quantiles in various empirical settings.This paper investigates the conditions under which regression quantiles can be estimated by estimating conditional means. The proposed method allows the use of techniques valid for estimating conditional means while providing insights into how regressors affect the entire conditional distribution. It is not intended to replace the well-established quantile regression estimator but offers an alternative approach for estimating regression quantiles in challenging settings. The method is particularly useful in panel data models with individual effects and models with endogenous explanatory variables. The paper presents an estimator that combines estimates of location and scale functions, both identified by conditional expectations. It also includes a simulation study, two empirical applications, and discusses possible extensions. The approach is computationally efficient and allows for the estimation of regression quantiles without crossing, a crucial property often overlooked in empirical applications. The paper also addresses the incidental parameters problem in panel data models and provides a solution for estimating structural quantile functions in the presence of endogenous regressors. The proposed estimator is compared with existing methods, and its performance is evaluated through simulations and empirical examples. The results show that the estimator performs well, especially when bias-corrected, and is computationally efficient. The paper concludes that the proposed method is a useful tool for estimating regression quantiles in various empirical settings.