English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 51281/86342 (59%)
造訪人次 : 8150771      線上人數 : 105
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/105348


    題名: 以修改ELECTRE III為核心的多準則群體決策支援之研究
    其他題名: A study on multi-criteria group decision support based on modified ELECTRE III for DMs’ risk preferences
    作者: 吳汶璞;Wu, Wen-Pu
    貢獻者: 淡江大學管理科學學系碩士班
    時序時;Shih, Hsu-Shih
    關鍵詞: 群體決策;效用函數;風險偏好;滿意指標;不滿意指標;模擬;ELECTRE III;Group decision;Utility function;risk preference;Concordance index;Discordance index;simulation
    日期: 2015
    上傳時間: 2016-01-22 14:53:48 (UTC+8)
    摘要: 本研究目的在藉由探討決策者的風險偏好,修改ELECTRE III優勢關係評估法,並與群體決策整合於一多準則群體決策模型,以利決策支援。並以台灣電子廢棄物回收處理廠的績效評估進行案例分析,以顯示本群體決策支援模型的實務價值。
    ELECTRE考量滿意指標、不滿意指標與否定門檻值,而ELECTRE III放寬前述門檻為一函數關係,本修改模型即以效用函數取代直線函數,並整合不同決策者的指標與門檻範圍,以掌握決策者的風險偏好與群體態度。藉由調整模型中的風險參數,以代表決策者不同的風險偏好,並帶入群體決策中整合所有決策者的門檻值與權重,最後比較原始模型、具有風險偏好模型與群體決策模型三者之間的差異性。經由模型檢驗中的敏感度分析、排序檢定與模擬分析,測試本研究修改模型的穩定型以及與原始模型排序之差異。
    分析結果顯示,修改後ELECTRE III模型可提供與原始ELECTRE III相異的方案排序,表示前者可有效將決策者風險偏好表現在方案排序中,且從結果中顯示原始模型的排序與風險中立的排序相同,可驗證本修改模型為一般性之表達。考量不同態度的群體決策之排序結果亦與個人決策的排序結果相異,代表本研究所建構之模型適用於不同決策類型。模型檢驗中的敏感度分析與排序檢定結果也顯示本修改模型具有穩定性,可依照決策者偏好進行參數調整。另在不同條件下的模擬分析結果顯示15家廠商的分級結果相當穩定,足以支援環保署進行分及補貼及輔導決策之依據。
    This study aims to formulate a decision maker’s (DM’s) risk preferences to modify ELECTRE (ELimination Et Choix Traduisant la REalité, or ELimination and Choice Expressing REality) III model, and integrate with group attitude for a multi-criteria group decision model to assist the decision support and make practical implication prominent.
    We employ concave and convex utility functions to modify the concordance and discordance indices in order to represent the DM’s risk preferences. Using group decision to comprehensive all DMs’ thresholds and weights then compared the difference between the original, modified and group decision models. We execute sensitivity analyses on different weights and thresholds as to demonstrate the stability of our proposed model. We also use ranking test and simulation to test the correlation between the traditional and modified models. After these testing, found the modified model fairly stable and can provide decision makers to make effective and reasonable decisions.
    The result shows the difference between traditional and modified models’ ranking, and we found that the original model’s rank is same as risk neutral. Group decision also can provide a different rank for DM, so we can verify that the modify model has stability, and DMs can have a
    decision model that fit the preferences by adjust the weight and thresholds. The result of rank and simulation also can help DMs sorting the alternatives, giving EPA the standard of subsidy and guidance.
    顯示於類別:[管理科學學系暨研究所] 學位論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML48檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋