AI SearchForecasting based on time series using different smoothing techniques
Call Number: AIT Thesis no. 1373 Material type:
TextSeries: Asian Institute of Technology. Thesis ; no. 1373Publication details: Bangkok : Asian Institute of Technology, 1978Description: 64 pSubject(s): Online resources: Dissertation note: Thesis (M.Sc.) - Asian Institute of Technology, 1978 Summary: One common way of modeling a time series is to find a transformation that reduces the observed data to random noise. Earlier procedures for technological forecasting based on time series data were of a some what ad-hoc nature, though theoretical justifications for their use were generally available. This study attempts to introduce a more powerful tool in technological forecasting based on time series by using Box-Jenkins approach, which is a newly developed technique. The basic concept and mathematical models of moving averages, exponential smoothing, and Box-Jenkins methodology are outlined and illustrated by their application to three time series concerned with technological forecasting. Comparison is then made by use of sum of squares of lead- 3 forecast error.
| Cover image | Item type | Current library | Home library | Collection | Shelving location | Call number | Materials specified | Vol info | URL | Copy number | Status | Notes | Date due | Barcode | Item holds | Item hold queue priority | Course reserves | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
20-AIT Publication
|
Asian Institute of Technology Library AIT Publications | AIT Thesis no. 1373 (Browse shelf(Opens below)) | 1 | Available | 30050004430558 | |||||||||||||
40-Archives
|
Asian Institute of Technology Library Archives | AIT Thesis no. 1373 (Browse shelf(Opens below)) | Available | 30050160082003 |
A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science of the Asian Institute of Technology, Bangkok, Thailand
Thesis (M.Sc.) - Asian Institute of Technology, 1978
One common way of modeling a time series is to find a transformation that reduces the observed data to random noise. Earlier procedures for technological forecasting based on time series data were of a some what ad-hoc nature, though theoretical justifications for their use were generally available. This study attempts to introduce a more powerful tool in technological forecasting based on time series by using Box-Jenkins approach, which is a newly developed technique. The basic concept and mathematical models of moving averages, exponential smoothing, and Box-Jenkins methodology are outlined and illustrated by their application to three time series concerned with technological forecasting. Comparison is then made by use of sum of squares of lead- 3 forecast error.
There are no comments on this title.