Record Details

PENGGUNAAN MODEL REGRESI TOBIT UNTUK MENGANALISA FAKTOR-FAKTOR YANG BERPENGARUH TERHADAP KEPUASAN KONSUMEN UNTUK JASA PENGANGKUTAN BARANG

Journal of Management and Entrepreneurship

View Archive Info
 
 
Field Value
 
Title PENGGUNAAN MODEL REGRESI TOBIT UNTUK MENGANALISA FAKTOR-FAKTOR YANG BERPENGARUH TERHADAP KEPUASAN KONSUMEN UNTUK JASA PENGANGKUTAN BARANG
 
Creator Suhardi, Imelda Yuliana; Alumni, Faculty of Economics, Petra Christian University
Llewelyn, Richard; Faculty of Economics, Petra Christian University
 
Subject ordinary least squares (OLS), Tobit, censured dependen variable.
 
Description This research compares the regression results of OLS and Tobit methods to analyze the effects of age, educational level and the type of good shipped on consumer satisfaction for the service of shipping goods between Surabaya and Sumbawa by PT Antar Nusa by ship.
If OLS is used with censured data, that is, if the value of the dependent variable (in this case, customer satisfaction) is limited in its value, the result of the regression will be biased and inconsistent. Because of that, the Tobit method can be used so that the result is better and more useful.
Based on the OLS results for this analysis, there are no variables that significantly influence customer satisfaction. This shows the weakness of the OLS method for censured data.
According to the results for the Tobit method, there are two variables which are significant, age and type of good. Age is positively related to satisfaction while for type of good shipped, customers who send business or trade goods are less satisfied than those who send personal goods. The level of education is not significant in any case.
The results suggest that researchers should use the Tobit method of regression for censured data so that the results will be correct, consistent and unbiased.


Abstract in Bahasa Indonesia :

Penelitian ini membandingkan hasil regresi OLS dan Tobit untuk menganalisa pengaruh dari variabel umur, tingkat pendidikan, serta jenis barang terhadap kepuasan konsumen untuk jasa pengangkutan barang di perusahaan PT Antar Nusa yang mengangkut barang antara Surabaya dan pulau Sumbawa dengan kapal laut.
Jika metode OLS digunakan dengan data yang terbatas, yaitu jika nilai dari variabel tidak bebas (kepuasan pelanggan) dibatasi, maka hasil regresi akan menjadi bias dan tidak konsisten. Oleh karena itu, metode Tobit dapat digunakan supaya hasil menjadi lebih baik dan berguna.
Berdasarkan hasil OLS dalam analisa ini, tidak ada variabel yang berpengaruh secara signfikan terhadap kepuasan pelanggan. Hal ini membuktikan kelemahan metode OLS untuk data yang terbatas.
Menurut hasil dari metode Tobit, ada dua variabel yang signifikan, yaitu umur dan jenis barang. Umur berpengaruh positif terhadap kepuasan pelanggan sedangkan untuk jenis barang, pelanggan yang mengirim barang usaha atau barang dagangan ternyata kurang puas dibandingkan orang yang mengirim barang pribadi. Tingkat pendidikan tidak berpengaruh.
Berdasarkan hasil tersebut disarankan kepada para peneliti, bahwa jika data untuk variabel tidak bebas menjadi terbatas, sebaiknya metode Tobit digunakan supaya hasil menjadi benar, konsisten dan tidak bias.

Kata kunci: ordinary least squares (OLS), Tobit, variable tidak bebas terbatas.
 
Publisher Institute of Research and Community Outreach - Petra Christian University
 
Date 2004-06-04
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
 
Identifier http://jurnalmanajemen.petra.ac.id/index.php/man/article/view/15613
10.9744/jmk.3.2.pp. 106-112
 
Source Jurnal Manajemen dan Kewirausahaan; Vol 3, No 2 (2001): SEPTEMBER 2001; pp. 106-112
 
Language eng
 
Relation http://jurnalmanajemen.petra.ac.id/index.php/man/article/view/15613/15605
 
Rights Authors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).