6多元回归分进一步问题.ppt

Multiple Regression Analysis;Multiple Regression Analysis多元回归分析;Chapter Outline 本章大纲;Lecture Notes 课堂笔记;Redefining Variables重新定义变量;Redefining Variables: An example重新定义变量：一个例子;Table 6.1;Impact of changing the scale of the dependent variable改变被解释变量测度单位的影响;Impact of changing the scale of the dependent variable改变被解释变量测度单位的影响;Impact of changing the scale of the independent variable改变解释变量测度单位的影响;Impact of changing the scale of the independent variable改变解释变量测度单位的影响;Redefining Variables重新定义变量;Redefining Variables重新定义变量;Beta Coefficients Beta系数;Beta Coefficients Beta系数;Beta Coefficients Beta系数;Beta Coefficients Beta系数;Beta Coefficients Beta系数;Functional Form 函数形式;Interpretation of Log Models对数模型的解释;Why use log models?为什么使用对数模型？;Some Rules of Thumb一些经验法则;Some Rules of Thumb一些经验法则;Limitations of Logs对数形式的限制;Cautions in using Logs慎重使用对数形式;Cautions in using Logs慎重使用对数形式;Quadratic Models含二次式的模型;Quadratic Models含二次式的模型;Quadratic Models含二次式的模型;Quadratic Models含二次式的模型;3.73;More on Quadratic Models对含二次式模型的进一步讨论;More on Quadratic Models对含二次式模型的进一步讨论;Interaction Terms交叉项;Interaction Terms交叉项;Interaction Terms交叉项;More on Goodness-of-Fit and Selection of Regressors拟合优度和解释变量选择的进一步探讨;More on Goodness-of-Fit and Selection of Regressors拟合优度和解释变量选择的进一步探讨;More on Goodness-of-Fit and Selection of Regressors拟合优度和解释变量选择的进一步探讨;Using Adjusted R-Sqrared to Choose Between Nonnested Models利用调整的R2在两个非嵌套模型中进行选择;Using Adjusted R-Squared to Choose Between Nonnested Models利用调整的R2在两个非嵌套模型中进行选择;Using Adjusted R-Squared to Choose Between Nonnested Models利用调整的R2在两个非嵌套模型中进行选择;Prediction Analysis: the estimator预测分析：估计量; ;Prediction Analysis: the Confidence Interval预测分析：置信区间;Prediction Analysis: Confidence Interval for a particular y预测分析：一个特殊y的置信区间;Prediction Analysis: Prediction Interval for y0预测分析： y0的预测区间;Prediction Analysis: Prediction Interval for y0预测分析： y0的预测区间; Sometimes, it is useful to examine individual observations to see whether the actual value of the dependent