Observed characteristics and teacher quality: Impacts of sample selection on a value added model

We measure the impact of observed teacher characteristics on student math and reading proficiency using a rich dataset from Florida. We expand upon prior work by accounting directly for nonrandom attrition of teachers from the classroom in a sample selection framework. We find evidence that sample selection is present in the estimation of the influence of teacher characteristics, but that failure to account for it does not appear to substantially bias estimation. Further, our procedure produces some evidence that more effective teachers are more likely to exit the classroom.

► Paper evaluates the influence of non-random attrition of teachers from the profession when estimating the effect of observed characteristics on student achievement.
► The paper adopts a modified version of the Heckit model to account for sample selection.
► Results indicate that sample selection is present when estimating the effect of teacher characteristics on student achievement; however, accounting for sample selection does not substantially alter the estimation of parameters.
► Estimates indicate that pre-service training received by a teacher has little to no influence on student achievement. However, some pedagogy coursework is significantly related to student achievement.
► Paper provides some evidence that higher quality teachers are more likely to leave the classroom in the first few years of employment.