This paper presents a general nonlinear logit model for analyzing political choice data, assuming probabilistic voting based on a spatial utility function. The parameters of the utility function and the spatial coordinates of choices and choosers can be estimated from observed choices. The model is implemented in the NOMINATE program for one-dimensional analysis of two-alternative choices with no nonvoting. The robustness and face validity of the program outputs are evaluated using roll call voting data from the U.S. Senate for 1979-1981, and extensive Monte Carlo studies are conducted. The methodology is also briefly illustrated with substantive applications to the Senate data. The paper discusses the theoretical issues and practical implementation of the model, including the estimation of the utility function and the spatial coordinates of legislators and alternatives. It addresses challenges such as perfect roll calls, unanimous roll calls, random roll calls, and legislators who vote perfectly or unpredictably. The results show that the model is robust to various changes in the utility function, iteration methods, and starting values, and that it effectively recovers the spatial positions of legislators and alternatives.This paper presents a general nonlinear logit model for analyzing political choice data, assuming probabilistic voting based on a spatial utility function. The parameters of the utility function and the spatial coordinates of choices and choosers can be estimated from observed choices. The model is implemented in the NOMINATE program for one-dimensional analysis of two-alternative choices with no nonvoting. The robustness and face validity of the program outputs are evaluated using roll call voting data from the U.S. Senate for 1979-1981, and extensive Monte Carlo studies are conducted. The methodology is also briefly illustrated with substantive applications to the Senate data. The paper discusses the theoretical issues and practical implementation of the model, including the estimation of the utility function and the spatial coordinates of legislators and alternatives. It addresses challenges such as perfect roll calls, unanimous roll calls, random roll calls, and legislators who vote perfectly or unpredictably. The results show that the model is robust to various changes in the utility function, iteration methods, and starting values, and that it effectively recovers the spatial positions of legislators and alternatives.