|
Activity Number:
|
508
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 7, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Social Statistics Section
|
| Abstract - #302099 |
|
Title:
|
The Causal Effect of Class Size on Academic Performance: Multivariate Instrumental Variable Estimators with Tennessee Class Size Data Missing at Random
|
|
Author(s):
|
Yongyun Shin*+ and Stephen W. Raudenbush
|
|
Companies:
|
The University of Chicago and The University of Chicago
|
|
Address:
|
Department of Sociology, Room 417, Chicago, IL, 60637,
|
|
Keywords:
|
Causal Effect ; Class Size ; Ignorably Missing ; Instrumental Variable ; Maximum Likelihood ; Simultaneous Equation Model
|
|
Abstract:
|
Does reduced class size cause higher academic achievement in reading, mathematics, listening and word recognition skills? How large are the effects? Do they vary across schools? To address the questions, we analyze data from Tennessee's Student/Teacher Achievement Ratio study of 1985. We estimate a three-level multivariate simultaneous equation model with an instrumental variable (IV) via maximum likelihood to analyze the data. The IV, random assignment of students to a small or regular class, reduces class size which by hypothesis improves academic achievement. We extend single-level Rubin's Causal Model to three levels. The method handles ignorably missing data with a general missing pattern using all available data. The results show that reduced class size improves the four test scores from kindergarten to third grade. We find that the causal effects of class size are homogeneous.
|
