The np package in R provides a variety of nonparametric and semiparametric kernel-based estimators for econometricians. It includes methods for nonparametric tests of significance and consistent model specification tests for parametric mean and quantile regression models. The package is designed to handle mixed data types, including continuous, unordered, and ordered categorical variables. Data-driven bandwidth selection is emphasized, though it can be computationally intensive. The np package allows users to create their own routines using high-level functions rather than writing in C or Fortran. It supports both data frame and formula interfaces for interacting with functions. The package includes a range of methods for density estimation, bandwidth selection, conditional mean and gradient estimation, conditional quantile and gradient estimation, model specification tests, and semiparametric regression. The np package is available from CRAN and includes functions for nonparametric regression, binary and multinomial outcome models, unconditional and conditional PDF and CDF estimation, and nonparametric quantile regression. The package is flexible and extensible, allowing users to perform a wide range of econometric analyses. The np package is particularly useful for handling mixed data types and provides efficient nonparametric methods that can outperform parametric models in certain situations.The np package in R provides a variety of nonparametric and semiparametric kernel-based estimators for econometricians. It includes methods for nonparametric tests of significance and consistent model specification tests for parametric mean and quantile regression models. The package is designed to handle mixed data types, including continuous, unordered, and ordered categorical variables. Data-driven bandwidth selection is emphasized, though it can be computationally intensive. The np package allows users to create their own routines using high-level functions rather than writing in C or Fortran. It supports both data frame and formula interfaces for interacting with functions. The package includes a range of methods for density estimation, bandwidth selection, conditional mean and gradient estimation, conditional quantile and gradient estimation, model specification tests, and semiparametric regression. The np package is available from CRAN and includes functions for nonparametric regression, binary and multinomial outcome models, unconditional and conditional PDF and CDF estimation, and nonparametric quantile regression. The package is flexible and extensible, allowing users to perform a wide range of econometric analyses. The np package is particularly useful for handling mixed data types and provides efficient nonparametric methods that can outperform parametric models in certain situations.