摘要
Quantile regression is gradually emerging as a powerful tool for estimating models of conditional quantile functions, and therefore research in this area has vastly increased in the past two decades. This paper, with the quantile regression technique, is the first comprehensive longitudinal study on mathematics participation data collected in Alberta, Canada. The major advantage of longitudinal study is its capability to separate the so-called cohort and age effects in the context of population studies. One aim of this paper is to study whether the family background factors alter performance on the mathematical achievement of the strongest students in the same way as that of weaker students based on the large longitudinal sample of 2000, 2001 and 2002 mathematics participation longitudinal data set. The interesting findings suggest that there may be differential family background factor effects at different points in the mathematical achievement conditional distribution.
基金
Supported by the National Natural Science Foundation of China (No. 10431010)
Education Ministry Key Project (No. 05JJD910001)
National Philosophy and Social Science Foundation grant (No. 07BTJ002)
2006 New Century Excellent Talent Program and Funds supported by Renmin University of China (No. 2006031611)
