Abstract
Various technological forecasting models have been proposed to represent the time pattern of technological growths. Of six such models studied, some models do significantly better than others, especially at low penetration levels, in predicting future levels of growth. Criteria for selecting an appropriate model for technological growth model are examined in this study. Two major characteristics were selected which differentiate the various models ; the skew of the curve and the underlying assumptions regarding the variance of the error structure of the model. Although the use of statistical techniques stil requires some subjective input and interpretations, this study provides some practical procedures in the selection of technological growth models and helps to reduce or control the potential source of judgmental error inconsistencies in the analyst's decision.