Melola Discovery

← Melola Discovery

Journal

PERBANDINGAN METODE PARTIAL LEAST SQUARE (PLS) DAN PRINCIPAL COMPONENT REGRESSION (PCR) UNTUK MENGATASI MULTIKOLINEARITAS PADA MODEL REGRESI LINEAR BERGANDA

Unnes Journal of Mathematics · Vol. 6 No. 2 (2018) · pp. 117–128

DOI
10.15294/ujm.v6i2.11819
ISSN
2460-5859, 2252-6943
Published
2018-01-09
Publisher
Universitas Negeri Semarang
Language
eng

Abstract

Salah satu asumsi analisis regresi linear berganda yaitu tidak terjadi masalah multikolinearitas. Apabila terjadi masalah multikolinearitas, metode Partial Least Square (PLS) dan Principal Component Regression (PCR) merupakan dua metode yang dapat digunakan untuk mengatasi masalah multikolinearitas tersebut. Metode yang digunakan dalam penelitian ini adalah Partial Least Square (PLS) dan Principal Component Regression (PCR) dengan data anggaran pendapatan Daerah Provinsi Jawa Tengah 2013. Hasil dari penelitian ini diperoleh model persamaan regresi dengan metode Partial Least Square (PLS) yaitu dan model persamaan regresi dengan metode Principal Component Regression (PCR) yaitu. Selanjutnya dipilih metode terbaik dengan menggunakan kriteria nilai tertinggi dan MSE terkecil. Pemilihan metode terbaik adalah dengan melihat nilai tertinggi dan MSE terkecil. Dapat disimpulkan bahwa metode yang lebih baik adalah Partial Least Square dengan nilai = 0,7752 dan nilai MSE yang dihasilkan Partial Least Square = 3,660671E16. One of analysis assumptions of bifilar linier regression is there is no multikolinearity problem occurs. If there is a multikolinearity problem occurs, Partial Least Square (PLS) and Principal Component Regression (PCR) methods are can used to solve the multikolinearity problem. The method that was used in this research were Partial Least Square (PLS) and Principal Component Regression (PCR) by using the data of budgeting income of Central Java in 2013. The result of this research was gotten a model of regression equation by using Partial Least Square (PLS) method it was and a model of regression equation by using Principal Component Regression (PCR) it was. After that choose the best method selection criteria was by seeing at the highest score and the lowest MSE. The best method selection was by seeing at the highest score and the lowest MSE. Thus, it could be concluded that Partial Least Square with the score of = 0,7752 and the MSE score that was resulted by Partial Least Square = 3,660671E16.

Collaboration network of the authors

40 authors · 201 co-authorship links · 4 across different organisations · showing the 40 most connected

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • State University of Semarang
  • Universitas Airlangga
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Putriaji HendikawatiAffiliation unknown11
Emi PujiastutiState University of Semarang9
Mulyono MulyonoAffiliation unknown8
Kartono KartonoUniversitas Airlangga7
Amin SuyitnoAffiliation unknown6
Masrukan MasrukanState University of Semarang6
St. Budi WaluyaAffiliation unknown5
Wardono WardonoAffiliation unknown5
Arief AgoestantoAffiliation unknown5
Mohammad AsikinAffiliation unknown4
Isnarto IsnartoAffiliation unknown3
Sunarmi SunarmiAffiliation unknown3
Zaenuri ZaenuriState University of Semarang3
Dwijanto DwijantoAffiliation unknown3
YL SukestiyarnoAffiliation unknown3
Isti HidayahAffiliation unknown3
Farida NursyahidahState University of Semarang2
Kristina WijayantiState University of Semarang2
Nurkaromah DwidayatiAffiliation unknown2
Yuninda Diah PratiwiAffiliation unknown2
Walid WalidState University of Semarang2
Aisyah Fany AchmaliaAffiliation unknown2
Endang SetyowatiAffiliation unknown2
Prihatina HikmasariAffiliation unknown2
Kristina WijayantiAffiliation unknown2
Stevanus Budi WaluyaAffiliation unknown2
Muhammad KharisAffiliation unknown2
Zaenuri MasturAffiliation unknown2
WardonoState University of Semarang1
Wardono WardonoState University of Semarang1
Sumliyah SumliyahAffiliation unknown1
Nyree AniAffiliation unknown1
Hendri HandokoAffiliation unknown1
Li Wei MingAffiliation unknown1
Muhamad Irwan HaqiqiAffiliation unknown1
Agus YuliantoAffiliation unknown1
Dwi Agung FitriantiAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/sju/index.php/ujm/oai, first harvested 6 Nov 2026, last seen 6 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">PERBANDINGAN METODE PARTIAL LEAST SQUARE (PLS) DAN PRINCIPAL COMPONENT REGRESSION (PCR) UNTUK MENGATASI MULTIKOLINEARITAS PADA MODEL REGRESI LINEAR BERGANDA</dc:title>
	<dc:creator>Supriyadi, Eko</dc:creator>
	<dc:creator>mariani, scolastika</dc:creator>
	<dc:creator>sugiman, sugiman</dc:creator>
	<dc:description xml:lang="en-US">Salah satu asumsi analisis regresi linear berganda yaitu tidak terjadi masalah multikolinearitas. Apabila terjadi masalah multikolinearitas, metode Partial Least Square (PLS) dan Principal Component Regression (PCR) merupakan dua metode yang dapat digunakan untuk mengatasi masalah multikolinearitas tersebut. Metode yang digunakan dalam penelitian ini adalah Partial Least Square (PLS) dan Principal Component Regression (PCR) dengan data anggaran pendapatan Daerah Provinsi Jawa Tengah 2013. Hasil dari penelitian ini diperoleh model persamaan regresi dengan metode Partial Least Square (PLS) yaitu dan model persamaan regresi dengan metode Principal Component Regression (PCR) yaitu . Selanjutnya dipilih metode terbaik dengan menggunakan kriteria nilai &amp;nbsp;tertinggi dan MSE terkecil.&amp;nbsp; Pemilihan metode terbaik adalah dengan melihat nilai &amp;nbsp;tertinggi dan MSE terkecil. Dapat disimpulkan bahwa metode yang lebih baik adalah Partial Least Square dengan nilai &amp;nbsp;= 0,7752 dan nilai MSE yang dihasilkan Partial Least Square = 3,660671E16.
&amp;nbsp;
One of analysis assumptions of bifilar linier regression is there is no multikolinearity problem occurs. If there is a multikolinearity problem occurs, Partial Least Square (PLS) and Principal Component Regression (PCR) methods are can used to solve the multikolinearity problem. The method that was used in this research were Partial Least Square (PLS) and Principal Component Regression (PCR) by using the data of budgeting income of Central Java in 2013. The result of this research was gotten a model of regression equation by using Partial Least Square (PLS) method it was   and a model of regression equation by using Principal Component Regression (PCR) it was . After that choose the best method selection criteria was by seeing at the highest  &amp;nbsp;score and the lowest MSE. The best method selection was by seeing at the highest  &amp;nbsp;score and the lowest MSE. Thus, it could be concluded that Partial Least Square with the score of  &amp;nbsp;= 0,7752 and the MSE score that was resulted by Partial Least Square = 3,660671E16.</dc:description>
	<dc:publisher xml:lang="en-US">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2018-01-09</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/sju/ujm/article/view/11819</dc:identifier>
	<dc:identifier>10.15294/ujm.v6i2.11819</dc:identifier>
	<dc:source xml:lang="en-US">Unnes Journal of Mathematics; Vol 6 No 2 (2017); 117-128</dc:source>
	<dc:source>2460-5859</dc:source>
	<dc:source>2252-6943</dc:source>
	<dc:source>10.15294/ujm.v6i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/sju/ujm/article/view/11819/9671</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2018 Unnes Journal of Mathematics</dc:rights>
</oai_dc:dc>