政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/133843
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 113318/144297 (79%)
造访人次 : 50974808      在线人数 : 867
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧：
  • 您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果
  • 若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据
    •  进阶搜寻
    政大機構典藏 > 商學院 > 統計學系 > 學位論文 >  Item 140.119/133843


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/133843


    题名: 邏輯斯迴歸與隨機森林預測能力比較探討
    A Comparative Study of Predictive Performance between Logistic Regression and Random Forest
    作者: 陳柏勳
    Chen, Bo-Xun
    贡献者: 黃子銘
    Huang, Tzee-Ming
    陳柏勳
    Chen, Bo-Xun
    关键词: 邏輯斯迴歸
    隨機森林
    B-spline
    Logistic regression
    Random forest
    日期: 2020
    上传时间: 2021-02-01 13:59:39 (UTC+8)
    摘要: 在針對二元變數的預測中，邏輯斯迴歸往往會被選為比較的對象之一。而在許多預測的競賽之中，邏輯斯迴歸所產生的預測結果，往往差強人意。因此本研究將針對邏輯斯迴歸與隨機森林比較的問題進行探討。在本研究中，對於邏輯斯迴歸之所以會輸於隨機森林表現的原因歸結在模型複雜度，並針對此點去設計模擬比較傳統邏輯斯迴歸、以 additive B­spline 和 tensor product B­spline 為基底的邏輯斯迴歸模型以及隨機森林四個模型，最終在模擬的設定下，結果得出後三個模型僅具有些微差距，而與傳統邏輯斯迴歸差距甚遠。因而歸結出在模型比較上，應該要先避免邏輯斯迴歸低度配適的問題，再行比較，才較為公平。
    In the prediction of binary variables, logistic regression is often selected asbase line for comparing. In many competitions, the prediction performancesof logistic regression are often unsatisfactory. Therefore, this study will dis­cuss the comparison between logistic regression and random forest. In this study, we design a simulation to compare traditional logistic regression, ad­ditive B­spline logistic regression, tensor product B-­spline logistic regression and random forest. The results showed that the latter three models only have a slightly different performance, which is far from the traditional logistic re­gression. Hence, if we want the comparison to be more fair, we need to deal with the problem of underfitting of logistic regression first.
    參考文獻: Bessaoud, F., Daures, J.­P., and Molinari, N. (2005). Free knot splines for logistic models and threshold selection. Computer methods and programs in biomedicine, 77(1):1–9.

    Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.

    De Boor, C. (1972). On calculating with b­splines. Journal of Approximation theory,6(1):50–62.

    Hastie, T. J. and Tibshirani, R. J. (1990). Generalized additive models, volume 43. CRC press.

    Huang, T. M. (2019). A knot selection algorithm for regression splines. 62nd ISI World Statistics Congress, Kuala Lumpur.

    Kay, R. and Little, S. (1987). Transformations of the explanatory variables in the logistic regression model for binary data. Biometrika, 74(3):495–501.

    Leathwick, J., Elith, J., and Hastie, T. (2006). Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions. Ecological Modelling, 199(2):188 – 196. Predicting Species Distributions.

    Li, M., Zhang, C., Xu, B., Xue, Y., and Ren, Y. (2020). A comparison of gam and gwr in modelling spatial distribution of japanese mantis shrimp (oratosquilla oratoria) in coastal waters. Estuarine, Coastal and Shelf Science, 244:106928.

    Wood, S. N. and Augustin, N. H. (2002). Gams with integrated model selection using penalized regression splines and applications to environmental modelling. Ecological Modelling, 157(2):157 – 177.
    描述: 碩士
    國立政治大學
    統計學系
    107354001
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0107354001
    数据类型: thesis
    DOI: 10.6814/NCCU202100027
    显示于类别:[統計學系] 學位論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    400101.pdf979KbAdobe PDF20检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈