Test Measurement Error and Inference from Value-Added Models

It is widely known that standardized tests are noisy measures of student learning, but value added models (VAMs) rarely take direct account of measurement error in student test scores. We examine the extent to which modifying VAMs to include information about test measurement error (TME) can improve inference. Our analysis is divided into two parts – one based on simulated data and the other based on administrative micro data from Missouri. In the simulations we control the data generating process, which ensures that we obtain accurate TME metrics with which to modify our value-added models. In the real-data portion of our analysis we use estimates of TME provided by a major test publisher. We find that inference from VAMs is improved by making simple TME adjustments to the models. This is a notable result because the improvement can be had at zero cost.