Harfianto, Unggul (2021) Pemodelan Konsumsi Rumah Tangga di Kota Surabaya Berdasarkan Hasil Proxy Mean Test Menggunakan Regresi Least Absolute Shrinkage and Selection Operator. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 06211740000055-Undergraduate Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
06211740000055-Undergraduate Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) |
Abstract
Kota Surabaya merupakan kota terbesar kedua di Indonesia. Penyelesaian masalah kemiskinan menjadi salah satu prioritas Pemerintah kota Surabaya hingga kini dengan harapan mengurangi angka kemiskinan melalui berbagai program. Pada kasus tingkat kesejahteraan di Kota Surabaya terdapat indikator yang banyak dalam mempengaruhi tingkat konsumsi rumah tangga yang mana sebagai ukuran dalam mengukur tingkat kesejahteraan. Hasil yang didapatkan pada General regression Least Square menunjukkan data terpengaruh multikolinearitas akibat dari korelasi antar variabel prediktor yang begitu kuat. Metode Regresi LASSSO digunakan untuk mengatasi masalah multikolinearitas tersebut. Dalam menentukan standar error dugaan parameter menggunakan bootstrap. Hasil penelitian ini menunjukkan bahwa terdapat 27 dari 55 variabel indikator tingkat kesejahteraan berpengaruh secara signifikans terhadap tingkat konsumsi. Disamping itu metode estimasi Regresi LASSO memiliki nilai MSE paling kecil dbandingkan regresi OLS, sehingga baik digunakan untuk mengestimasi tingkat konsumsi rumah tangga di Kota Surabaya serta dapat mengatasi masalah multikolinearitas
=====================================================================================================
Surabaya is the second biggest city in Indonesia. Solving the problem of poverty is one of the priorities of the Surabaya city government until now with the hope of reducing poverty through various programs. In the case of welfare level in Surabaya, there are many indicators that influence household consumption level as a measure in measuring the level of welfare. The result from General regression Least Square shows that the data is affected by multicollinearity as a result of strong correlation between predictor variables. LASSO regression method is used to solve that multicollinearity problem. Determination of the standard error of parameter estimates using the bootstrap method. The result of this research shows that there are 27 out of 55 variables of welfare level indicators that significantly influence the level of consumption. Besides that, LASSO regression estimation method has the smallest MSE score compared to OLS regression method, so LASSO regression estimation method is good for estimating the household consumption level in Surabaya and can overcome multicolinearity
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Konsumsi Rumah Tangga, LASSO, Mean Square Error, Multikolinearitas, Proxy Mean Test ==================================== Household consumption, LASSO, Mean Square Error, Multicolinearity, Proxy Mean Test |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Unggul Harfianto |
| Date Deposited: | 01 Sep 2021 01:35 |
| Last Modified: | 01 Sep 2021 01:35 |
| URI: | http://repository.its.ac.id/id/eprint/91297 |
Actions (login required)
 |
View Item |