End-use quality improvement is an important objective in most wheat breeding programs. In the case of winter wheat, the short duration between harvest and planting represents a major challenge for efficient and timely conduct of quality evaluations to enable selection prior to planting. Furthermore, multiple test parameters, some being destructive of the grain sample, are commonly used as predictors of overall end-use quality which further complicates the selection process. The large numbers of breeding samples typically handled even by programs of modest size represents another limitation in the process of quality evaluation and selection in a breeding program. Near-infrared reflectance (NIR) spectroscopy is a rapid and non-destructive technique that could facilitate early generation selection for end-use quality. The first step in the application of NIR spectroscopy technology in a wheat breeding program is to develop and evaluate prediction models. Prediction models for various end-use quality evaluations have been developed including single kernel characteristics and test weight. The next step includes evaluation and application of the prediction model in a breeding program. The objectives of this research were to determine the selection efficiency and accuracy of selection based on realized heritability and determination of classification errors when using NIR spectroscopy as a selection tool in wheat breeding.