《双因素设计.ppt

以 2F1模型为例，进行方差分析 可见， 2F1模型本身虽然显著的，但其中的互作AB对絮凝系数的影响没有显著性。 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 以 Quadratic模型为例，进行方差分析 可见，虽然 Quadratic模型本身是显著的，但因素的互作AB以及B2对絮凝系数的影响没有显著性。 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 最适宜的还是Linear模型，其方差分析结果为 可见，线性模型已能足够反映变量对絮凝系数的影响。即模型仅考虑两因素的主效应即可，而无需考虑其他变量或其组合。 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 选用 Linear模型的后续分析过程 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Analysis? Diagnostics Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Analysis? Model graphs :仅有单因子 由于 Linear模型中只有主效应 A和B，所以此处Term中就不再含有 AB Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Analysis? Model graphs :仅有单因子 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 如果选择 2F1模型或 Quadratic模型，则此处Term中也就会出现相应的选项，如 AB、B2等 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. * 双因素实验 : Part 1 ——实施前的设计 因素水平表 例子：“2_factor(均为名义变量).dx7” Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 此处 2个因素都被设置为分类变量中的名义变量（Nominal） Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 评估的关键作用：对你想选择的不同层次的模型 是否存在因素的别名或混杂现象，作出判断。 利于你正确设计实验，并通过实验实施后的分析 过程，求得相关感兴趣的参数。 双因素实验 : Part 2 ——实施前