An analysis and forecast of LRT demand using Arima models
This thesis is about forecasting LRT demand using the Univariate Box-Jenkins ARIMA models. It is a requirement in forecasting that the data must be stationary. Nonstationary data can be converted into a stationary data by differencing. There are four common processes used in forecasting these are Au...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Animo Repository
1996
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/etd_bachelors/16348 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Language: | English |
| Summary: | This thesis is about forecasting LRT demand using the Univariate Box-Jenkins ARIMA models. It is a requirement in forecasting that the data must be stationary. Nonstationary data can be converted into a stationary data by differencing. There are four common processes used in forecasting these are Autoregressive (AR), Moving Average (MA), Mixed (ARIMA) processes. There are three stages in obtaining an appropriate model before forecasting: (1) Identification, (2) Estimation, and (3) Diagnostic checking. Using the monthly LRT ridership starting from December 1984 to September 1996 as our data, a final model (an integrated mixed ARIMA model) was used to forecast the LRT demand beyond the period covered by the data used in this research. And with the final model, the researchers was able to forecast the LRT demand for the next 36 observations or three years from the last observation date. |
|---|