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

      Pengaruh Pendugaan Data Hilang terhadap Akurasi Pendugaan Koefisien Model SEM

      Thumbnail
      View/Open
      Cover (889.0Kb)
      Fullteks (2.432Mb)
      Lampiran (1.117Mb)
      Date
      2022
      Author
      Oktaviani, Christina
      Suharjo, Budi
      Purnaba, I Gusti Putu
      Metadata
      Show full item record
      Abstract
      Missing data dapat diatasi dengan menghapus responden yang memiliki missing data dari dataset atau menggunakan imputasi. Namun menghapus data yang tidak lengkap dan hanya menggunakan data yang lengkap saja, dapat mengakibatkan berkurangnya jumlah data yang sudah ditetapkan. Maka jika terdapat missing data cara yang terbaik dengan menggunakan imputasi. Dalam penelitian ini missing data diatasi dengan menggunakan mean imputation. Setiap metode imputasi memiliki karakteristiknya. Tujuan dari penelitian ini adalah untuk mempelajari dampak missing data terhadap akurasi pendugaan koefisien model SEM. Hasil penelitian menunjukkan bahwa semakin meningkatnya ukuran persentase missing data, maka nilai yang dihasilkan akan semakin bias. Akurasi menunjukkan bahwa metode mean imputation dalam mengatasi dampak missing data dengan persentase missing 5% cukup layak dalam menduga koefisien parameter model SEM. Sedangkan pada persentase missing data 10% dan 15% tidak akurat dalam menduga parameter model. Secara keseluruhan metode mean imputation layak digunakan jika persentasi missing data kurang dari 5%.
       
      Missing data can be overcome by removing respondents who have missing data from the dataset or using imputation. However, deleting incomplete data and only using complete data can result in a reduction in the amount of data that has been set. So if there is missing data, the best way is to use imputation. In this study, missing data was overcome by using mean imputation. Each imputation method has its characteristics. The purpose of this study was to study the impact of missing data on the accuracy of the estimation of the coefficients of the SEM model. The results showed that the increasing the size of the percentage of missing data, the resulting value will be more biased. Accuracy shows that the mean imputation method in overcoming the impact of missing data with a missing percentage of 5% is quite feasible in estimating the parameter coefficients of the SEM model. While the percentage of missing data is 10% and 15% is not accurate in estimating the model parameters. Overall, the mean imputation method is feasible if the percentage of missing data is less than 5%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/112545
      Collections
      • UT - Mathematics [1487]

      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