A Correlated Random Effects Model for Longitudinal Data with Non-ignorable Drop-Out: An Application to University Student Performance
Empirical study of university student performance is often complicated by missing data, due to student drop-out of the university. If drop-out is non-ignorable, i.e. it depends on either unobserved values or an underlying response process, it may be a pervasive problem. In this paper, we tackle the relation between the primary response (student performance) and the missing data mechanism (drop-out) with a suitable random effects model, jointly modeling the two processes. We then use data from the individual records of the faculty of Statistics at Sapienza University of Rome in order to perform the empirical analysis.
- Little, R.J.A. (2008). Selection and Pattern-Mixture Models, in Advances in Longitudinal Data Analysis, G. Fitzmaurice, M. Davidian, G. Verbeke and G. Nolenberghs (eds.), London: CRC Press.Google Scholar
- Rubin, D.B. (2000). The Utility of Counterfactuals for Causal Inference - Discussion of Causal Inference Without Counterfactuals by A. P. Dawid, Journal of the American Statistical Association, 95:435438.Google Scholar
- Schram, C.M. (1996). A Meta-Analysis of Gender Differences in Applied Statistics Achievement, Journal of Educational and Behavioral Statistics, 21:55–70.Google Scholar
- Zimmer, J. and Fuller, D. (1996). Factors Affecting Undergraduate Performance in Statistics: A Review of the Literature, paper presented at the Annual Meeting of the Mid-South Educational Research Association, Tuscalosa (AL), November.Google Scholar