Maulidiyah, PipingMaghfiroh (2014) Penerapan Metode Restricted Maximum Likelihood (Reml) Pada Pemodelan Autoregressive Sisaan Orde 1 Pada Data Saham. Sarjana thesis, Universitas Brawijaya.
Abstract
Saham adalah tanda kepemilikan seseorang atau badan dalam perusahaan atau perseroan terbatas. Pengamatan yang disusun menurut selang waktu yang sama disebut data deret waktu, misal data saham. Tujuan yang ingin dicapai dalam penelitian ini adalah menerapkan metode Restricted Maximum Likelihood (REML) pada model autoregressive sisaan orde satu pada data saham. Digunakan data saham mingguan adjusted close Astra Argo Lestari Tbk pada bulan Maret 2013 sampai Maret 2014. Identifikasi model menggunakan grafik ACF yang menurun secara eksponensial dan 1 lag pada grafik PACF, serta perubahan deviance yang menghasilkan model AR(1). Parameter model AR(1) diduga dengan metode REML. Kelebihan REML adalah menghasilkan penduga ragam tak bias. Pengujian asumsi kenormalan menggunakan uji Saphiro Wilk. Model AR(1) dengan metode REML memperkirakan harga saham adjusted closed minggu ini 502.224 rupiah ditambah 0.976 kali harga saham minggu lalu.
English Abstract
A share is defined as a person or a commission’s ownership in a company or a limited liability company. Time series refers to the sequence of observations which are ordered based on equal time-interval such as shares. This study aims at implementing the Restricted Maximum Likelihood (REML) method on the first order of residual autoregression. The data are the adjusted closing price of weekly stock of Astra argo Lestari Tbk, since March 2013 up to March 2014. Furthermore, in identifying the model, this study uses the exponentially-declined ACF graph, the 1 lag of PACF graph, as well as change of deviance which yields AR(1) model. REML method is used for estimating the parameter of AR(1) model. REML method is considered effective for estimating the unbiased variance. Normality of residual of AR(1) model is tested by Saphiro Wilks is used for testing the assumption of normality by estimating the adjusted closing price of stock of the week using the REML method, which means 502.224 rupiahs is added by 0.976 multiplied by every stock price last week.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/MIPA/2014/254/051404945 |
| Subjects: | 500 Natural sciences and mathematics > 510 Mathematics |
| Divisions: | Fakultas Matematika dan Ilmu Pengetahuan Alam > Matematika |
| Depositing User: | Budi Wahyono Wahyono |
| Date Deposited: | 28 Aug 2014 13:53 |
| Last Modified: | 21 Oct 2021 04:30 |
| URI: | http://repository.ub.ac.id/id/eprint/153879 |
Preview |
Text
SKRIPSI.pdf Download (2MB) | Preview |
Actions (login required)
 |
View Item |