Dynamic, multilevel and adaptive models for forecasting technological substitution | |
| Author | Chowdhury, H. R. M. H. Amir-E-Kabir |
| Call Number | AIT Diss. no.D17 |
| Subject(s) | Technological forecasting Technological innovations Dynamic programming |
| Note | A dissertation submitted in partial fulfillment of the requirements for the degree of Doctoral of Engineering. |
| Publisher | Asian Institute of Technology |
| Abstract | In this dissertation attempts have been made to study the phenomenon of technological substitution to a greater depth by developing models based primarily on trend extrapolation. In all, four models are presented here along with methods to improved the quality and reliability of model predictions. The first two models are for one-to-one substitution - (a) a generalized model of one-to-one technological substitution; and (b) a dynamic model 9of one-to-one technological substitution. All technological substitutions are not, however, one-to-one in nature. There are many instances where a recently introduced product or technology before gaining full market share from its older products (s) - a case of multilevel substitution. The remaining two models which deal with multilevel substitution. The remaining two models which deal with multilevel substitution, are (c) a multilevel model of technological substitution; and (d) a dynamic multilevel model of technological substitution. It has been shown that Blackman model, Fisher-Pry model and Floyd model are special cases of the generalized model. The generalized model can also incorporate the effects of various exogenous factors. The other three models developed in this research are extensions of the generalized model and are based on Forrester's system dynamics methodology. In addition to the forecasting of market share, the last three models can also forecast the actual size of the market of each of the competing technology or product. In dynamic model of one-to-one technological substitution, the parameters are made time dependent, so that model predictions can be updated continuously as varying circumstances influence the elements of the forecast. Multilevel substitution models are attempts to analyze the market dynamics under multilevel substitution conditions. In dynamic multilevel substitution model, the parameters are made time dependent in order to take into consideration the time varying effects of various exogenous factors in certain cases. Illustrative examples are included in this dissertation to demonstrate the usefulness as well as working principles of all models. |
| Year | 1975 |
| Type | Dissertation |
| School | AIT Publication (Year <=1978) |
| Department | Other Field of Studies (No Department) |
| Academic Program/FoS | Dissertation (D) (Year <=1978) |
| Chairperson(s) | Pakorn Adulbhan, |
| Examination Committee(s) | Sharif, Nawaz |
| Degree | Thesis (Ph.D.) - Asian Institute of Technology, 1975 |