Title

Student Sorting and Bias in Value Added Estimation: Selection on Observables and Unobservables

Author(s)

Jesse Rothstein Jesse Rothstein (Princeton University)

Abstract

Non-random assignments of students to teachers can bias value added estimates of teachers' causal effects. Rothstein (2008) shows that typical value added models indicate large counter-factual effects of 5th grade teachers on students' 4th grade learning, implying that assignments do not satisfy the imposed assumptions. This paper quantifies the resulting biases in estimates of 5th grade teachers' causal effects from several value added models, under varying assumprions about the assignment process. Under selection on observables, models for gain scores without controls or with only a single lagged score control are subject important bias, but models with controls for the full test score history are nearly free of bias. I consider several scenarios for selection on unobservables, using the across-classroom variance of observed variables to calibrate each. Results indicate that even well-controlled models may be substantially biased, with the magnitude of the bias depending on the amount of information available for use in classroom assignments.

Creation Date

2008-06

Section URL ID

ERS

Paper Number

26

URL

https://dataspace.princeton.edu/bitstream/88435/dsp016m311p33z/1/26ers.pdf

File Function

Jel

H75, I21, C12, C52, J33, J45

Keyword(s)

Suppress

false

Series

2