Excel求解运筹学问题.pptVIP

Figure 2.22 Graph showing the feasible region for the Profit Gambit Co. advertising-mix problem, where the ≥ functional constraints have moved this region up and away from the origin. Figure 12.19 The dialogue box used by the Plot option of SensIt. Figure 12.20 The graph generated by the Plot option of SensIt for the full Goferbroke Co. problem to show how the expected payoff (when using Bayes’ decision rule) depends on the prior probability of oil. Figure 12.21 The dialogue box used by the Spider option of SensIt. Figure 12.22 The spider graph generated by the Spider option of SensIt for the full Goferbroke Co. problem to show how the expected payoff (when using Bayes’ decision rule) varies with changes in any one of the cost or revenue estimates. Figure 12.23 Expansion of the spreadsheet in Figure 12.18 to prepare for generating a tornado diagram with SensIt. Figure 12.24 The dialogue box used by the Tornado option of SensIt. Figure 12.25 The tornado diagram generated by the Tornado option of SensIt for the full Goferbroke Co. problem to show how much the expected payoff (when using Bayes’ decision rule) can vary over the entire range of likely values of any one of the cost or revenue estimates. 最短路线为： O?A ?B ?E ?F ?T 最短路线为： O?A ?B ?E ?F ?T 5. 用Excel Solver 做线性回归分析 线性回归用来反映因变量与自变量之间的线性关系。应用线性回归，首先需要判断变量之间是否具有线性关系，这可以通过画散点图得到。画散点图的方法是： 1）选择画散点图的数据区域； 2）在插入菜单中选择插入“图表” 3）在图表对话框中选择散点图类型。 进一步，可以通过选择图表，在图表菜单条下选择添加趋势线，在添加趋势线对话框中，选择选项，显示公式和R2值 多元线性回归：y=a+b1x1+b2x2 例题：若某个公司的企业销售及有关变量数据如下表所示： 应用Excel中的数据分析工具，得到的多元回归结果如下： 回归方程如下： 预测值和残差 6.用Excel Solver 进行决策分析 A 出售 钻探 干涸(0.75) 有石油(0.25) -100 700 90 B 100 100 例：求解如下简单的决策树 TreePlan的安装: (1)首先从学习光盘中找到TreePlan程序模块; (2)将 TreePlan程序模块拷贝到Program files\Microsoft office\ Office\library\目录下; (3)在 Excel工具菜单中选择加载宏; (4)在加载宏对话框中选中 TreePlan程序; (5)回到Excel工具菜单中查看,是否有Decision Tree菜单条,如果有,则安装成功. 选择工具菜单条中的Decision Tree 点击创建新树,这样就创建了一个如下图所示的决策树 选中每一分枝末端，再一次点击决策树菜单，可以添加决策结点或状态结点。 用决策树做敏感性分析：通过建立电子表格和决策树之间数据的联系，可方