Ayuningtyas, Fitri (2019) Peramalan Jumlah Penumpang Pesawat Domestik Di Empat Bandara Utama Keberangkatan Menggunakan Metode Generalized Space-Time Autoregressive (GSTAR). Other thesis, Institut Teknologi Sepuluh Nopember.
|
Text
06111540000012-UnderGraduate_Theses.pdf Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Perkembangan jasa transportasi udara dalam negeri dapat dilihat dari jumlah penumpang pesawat domestik yang terus meningkat setiap tahunnya. Fenomena kenaikan jumlah penumpang pesawat pada periode mendatang, dapat dianalisis menggunakan model peramalan yang berdasarkan waktu dan lokasi. Pemodelan untuk peramalan jumlah penumpang yang melibatkan aspek waktu dan lokasi dapat menggunakan model Generalized Space Time Autoregressive (GSTAR). Estimasi parameter yang digunakan dalam model GSTAR adalah metode Ordinary Least Square (OLS) dan Generalized Least Square (GLS). Model GSTAR dengan estimasi OLS menghasilkan nilai parameter yang lebih tepat dan RMSE minimum. Hal ini disebabkan karena model GSTAR dengan estimasi OLS memenuhi asumsi residual tidak berkorelasi antar persamaan. Berdasarkan kriteria out sample, model GSTAR terbaik untuk data jumlah penumpang pesawat adalah model GSTAR-OLS(1_1) dengan bobot lokasi seragam karena memiliki nilai RMSE yang minimum. Model terbaik yang didapatkan memilki makna bahwa peramalan jumlah penumpang di bandara Soekarno-Hatta, Kualanamu, Ngurah-Rai dan Juanda dipengaruhi oleh jumlah penumpang pada bulan sebelumnya dan jumlah penumpang dilokasi yang lainnya pada bulan sebelumnya.
===============================================================================================================================
The development of domestic air transportation services can be seen from the number of domestic airplane passengers which continues to increase every year. The phenomenon of the increase in the number of aircraft passengers in the coming period can be analyzed using a forecasting model based on time and location. Modeling for forecasting the number of passengers involving aspects of time and location can use the Generalized Space-Time Autoregressive (GSTAR) model. The parameter estimates used in the GSTAR model are the Ordinary Least Square (OLS) and Generalized Least Square (GLS) methods. The GSTAR model with OLS estimation produces more precise parameter values and minimum RMSE. This is because the GSTAR model with OLS estimation satisfies the residual assumption does not correlate between equations. Based on the out sample criteria, the best GSTAR model for data on aircraft passenger numbers is the GSTAR-OLS(1_1 )model with uniform location weights because it has a minimum RMSE value. The best model obtained has the meaning that forecasting the number of passengers at Soekarno-Hatta, Kualanamu, Ngurah-Rai and Juanda airports is influenced by the number of passengers in the previous month and the number of passengers in other locations in the previous month.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Transportasi, Penumpang Pesawat, GSTAR-OLS, GSTAR-SUR |
| Subjects: | Q Science Q Science > QA Mathematics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Mathematics > 44201-(S1) Undergraduate Thesis |
| Depositing User: | Fitri Ayuningtyas |
| Date Deposited: | 06 Aug 2026 01:49 |
| Last Modified: | 06 Aug 2026 01:49 |
| URI: | http://repository.its.ac.id/id/eprint/66116 |
Actions (login required)
![]() |
View Item |
