[Sample B: Approval/Signature Sheet] - George Mason University
[Sample B: Approval/Signature Sheet] - George Mason University
[Sample B: Approval/Signature Sheet] - George Mason University
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
6.1 Varying Weights<br />
6. SENSITIVITY ANALYSIS<br />
In order to check the robustness of the alternative rankings, a sensitivity analysis<br />
was performed by varying the weights. The weights of the higher levels of the objective<br />
hierarchy are of particular importance because ―many of the weights at lower levels<br />
involve technical factors that limit the ability of non-experts to make the required<br />
judgments.‖ 120 Also, the high level weights represent policy judgments, and it is likely<br />
that they could be very different from decision maker to decision maker. 121<br />
Moreover, Winterfeldt and Edwards state that ―it is unlikely that the weight<br />
judgments at lower levels of the value tree deserve to be included in the sensitivity<br />
analysis. Important sensitivities to weights arise at higher levels of those trees.‖ 122<br />
Thus, the first part of the sensitivity analysis was focused on the variation of the<br />
weights of the highest level fundamental objectives: Force Application, Force Awareness,<br />
Force Mobility and Force Support.<br />
120 John C. Butler et al., ―The Adoption of Multiattribute Utility Theory for the Evaluation of Plutonium<br />
Disposition Options in the United States and Russia,‖ in Advances in Decision Analysis: From Foundations<br />
to Applications, ed. Ward Edwards, Ralph F. Miles Jr. Jr, and Detlof von Winterfeldt, 1st ed. (New York,<br />
NY: Cambridge <strong>University</strong> Press, 2007), 499.<br />
121 Ibid.<br />
122 Winterfeldt and Edwards, Decision Analysis and Behavioral Research, 414.<br />
79