View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Actuaria
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Actuaria
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Penentuan Sebaran Kerugian Agregat Menggunakan Metode Fast Fourier Transform

      No Thumbnail [100%x80]
      View/Open
      Cover (841.2Kb)
      Fullteks (1.122Mb)
      Lampiran (774.8Kb)
      Date
      2023
      Author
      Pratama, Muhammad Rhidwan
      Setiawaty, Berlian
      Ruhiyat
      Metadata
      Show full item record
      Abstract
      Kerugian agregat adalah total kerugian yang dapat dihitung dengan pendekatan sebaran gabungan (compound distribution), baik secara analitik maupun numerik. Penentuan sebaran kerugian agregat dilakukan untuk memodelkan klasifikasi kerugian agregat yang meliputi penghitungan Value at Risk (VaR) dan Expected Shortfall (ES). Secara analitik, penentuan sebaran gabungan menggunakan metode fungsi karakteristik itu rumit. Sebagai alternatif, penentuan sebaran gabungan dihitung menggunakan metode fast Fourier transform. Dari data klaim dataCar di package R, diperoleh banyaknya klaim mempunyai sebaran Zero Truncated Negative Binomial (ZTNB) serta besarnya klaim mempunyai sebaran Inverse Gaussian (IG) dan sebaran Lognormal (LN). Sebaran compound ZTNB–IG lebih baik memodelkan besar VaR, nilai harapan, dan ragam data dibandingkan sebaran compound ZTNB–LN. Sedangkan untuk ES, kedua sebaran compound dapat digunakan untuk menghampiri ES empirik pada tingkat kepercayaan 97%.
       
      Aggregate loss is total losses that can be calculated with a compound distribution approach, both analytically and numerically. Determination of the aggregate loss distribution is carried out to model the classification of aggregate losses which includes the calculation of Value at Risk (VaR) and Expected Shortfall (ES). Analytically, the determination of the compound distribution using the characteristic function method is complicated. Alternatively, the determination of the compound distribution can be calculated using the fast Fourier transform method. From the dataCar claim data in package R, frequency claims have a Zero Truncated Negative Binomial (ZTNB) distribution and severity claims have an Inverse Gaussian (IG) distribution and a Lognormal (LN) distribution. The compound ZTNB–IG distribution better models the size of VaR, expectation value, and variance from the data compared to the compound ZTNB–LN distribution. Meanwhile for the ES, the two compound distributions can be used to approximate the empirical ES at the 97% confidence level.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/116144
      Collections
      • UT - Actuaria [202]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      NoThumbnail