摘要
介绍了现场实验中“不等同对照组”问题对实验处理效应分析和推论准确性的影响,提出以“不等同对照组准实验设计”模式和协方差分析(ANCOVA)模型解决教育实验中的“不等同对照组”问题。ANCOVA模型使用一个或多个前测作为实验处理变量的“协变量”,可以校正由于“选择—成熟”因素带来的实验前各组之间固有的差异,提高实验结果推论的效度。
This paper discusses some major threats of the nonequivalence between experimental and control groups to draw valid inferences on whether the experimental treatment works. Several alternative solutions, such as the nonequivalent control group designs and the ANCOVA statistical analysis model are suggested. The ANCOVA with a single covariate or with multiple covariates extends the elementary ANOVA by including the single or multiple pretests in the model in the form of a linear regression. Using the pretests in this way provides an adjustment for initial differences between the groups due to ＂selectionmaturation＂.
出处
《西北师大学报（社会科学版）》
CSSCI
北大核心
2006年第4期66-70,共5页
Journal of Northwest Normal University(Social Sciences)
基金
广东省社科规划项目阶段性成果
