Stochastic models are developed in this article to examine the rate of test misgrading in educational and psychological measurement. The estimation of inadvertent grading errors can serve as a basis for quality control in measurement. Limitations of traditional Poisson models have been reviewed to highlight the need to introduce new models using well established geometric and negative binomial distributions. Equations are developed for the use of geometric and negative binomial distributions in the study of test misgrading. In this study, the geometric process is developed from a single-grader scenario under a policy of zero tolerance for test misgrading. The negative binomial process seems appropriate for state or national assessment that involves more than one test grader. Results of this investigation can be used to ensure the number of misgraded events below a threshold k. Features of the quality control measures are discussed in this article in a context of local and national assessments. (Contains 22 references.) (SLD)