需求規劃能幫助減少存貨並帶來利益，然而需求規劃最大問題為不確定性，因此利用準確預測方法幫助決策，層級式預測可供給企業層級不同使用者需要的資訊，而以供應鏈的角度而言，可供給供應鏈上各產業需要之預測資料，在過去研究中由上而下、中間往上往下、由下往上哪個方法比較好沒有一致性定論，有學者提出層級式預測績效與(1)產品內項目之相關性有關。(2)產品內項目預測誤差相關程度有關。(3)預測方法有關。因此為了增加層級式預測績效，本研究使用了群集分析將相關性高的產品項分為一群，並結合了成長曲線預測法與時間序列預測方法，增加預測準確性。目前台灣積極發產TFT-LCD產業，台灣也同時為筆記型電腦生產大國，TFT-LCD為筆記型電腦關鍵零組件。本研究以筆記型電腦液晶面板為實證研究對象，過去研究僅僅探討層級式預測由上而下、由中間往上往下、或由下往上哪個方法較好？本研究提出新的比較法則，由傳統方法(Top-Down，Middle-Out，Bottom-Up)進行多重比較，得到各層級的最佳配適模型，此方法可以大幅提升整體預測能力，得到整體預測結果最佳化。

Demand planning can reduce inventories effectively. But the difficulty of demand planning is uncertainty. So, we may use forecasting methods to help making decisions in the demand planning. Hierarchical forecasting render a variety of forecast information to various management levels within an organization. Similarly, it gives proper forecast information which different organizations need within the supply chain. In the past, there are three strategies about hierarchical forecasting which are “Top-Down”, “Middle-Out”, “Bottom-Up”. Which is the best？ There is no consist conclusions until now. Some scholars demonstrate the forecast performance is dependent on (1) the magnitude of correlation between the subaggregate forecast variable, (2) the magnitude of correlation between forecast errors of subaggregate variables, (3) the quality of forecasting techniques. To improve the performance of forecasting, we must cluster high correlation groups by using cluster analysis, then combine the methods of growth curve forecasting and time series models. TFT-LCD industry is growing in Taiwan. Also Taiwan is the biggest export country of notebook in the world. TFT-LCD is a major component for a notebook. The studies just compare “Top-Down, Middle-Out, Bottom-Up” in the past. We bring up a new comparative method. We proceeded muti-comparisons from traditional method and get the best fitting results. It makes overall optimization.

中文部分
[1]IT IS產業研究報告
[2]王淑珍，「台灣邁向液晶王國之祕」，臺北：中國生產力中心，2003。
[3]方世傑，「市場預測方法一百種」，臺北：書泉出版社，1996。
[4]春日井博，需求預測入門，臺北：書泉出版社，1988。
[5]羅心蓮，「層級式預測方法論-以液晶監視器為例」，國立清華大學工業工程與工程管理研究所碩士論文，2005。
英文部分
[1] Aigner, D. J. and Goldfeld, S. M., “Estimation and Prediction from Aggregate Data when Aggregates are Measured More Accurately than their Components”, Econometrica, Vol.42, No.1, pp.113-134, 1974.
[2] Box, G. E. P. and Jenkins, G. M., “Time Series analysis Forecasting and Control, 1st ed”, San Francisco : Holden-Day, 1970.
[3] Balasooriya, U., “Failure-censored Reliability Sampling Plans for the Exponential Distribution”, Journal of Statistical Computation and Simulation, Vol.52, No.4, pp.337-349, 1995.
[4] Barnea, A. and Lakonishok, J., “An Analysis of the Usefulness of Disaggregated Accounting Data for Forecasts of Corporate Performance.”, Decision Sciences, Vol.11, No.1, pp.17–26, 1980.
[5] Bass, F. M., “A New Product Growth for Model Consumer Durables”, Management Science, Vol.15, No.5, pp.215-227, 1969.
[6] Bodger, P. S. and Tay, H. S., “Logistic and Energy Substitution Models for Electricity Forecasting: A Comparison Using New Zealand Consumption Data”, Technological Forecasting and Social Change, Vol.31, No.1, pp.27-48, 1987.
[7] Collins, D. W., “Predicting Earning with Sub-entity Data: Some Further Evidence”, Journal of Accounting Research, Vol.14, No.1, pp.161-177, 1976.
[8] Dangerfield, B. J. and Morris, J. S., “Top-Down or Bottom-Up: Aggregate versus Disaggregate Extrapolations”, International Journal of Forecasting, Vol.8, No.2, pp.233-241, 1992.
[9] Dalrymple, D. J., “Results from a 1983 United States Survey”, International Journal of Forecasting, Vol.3, No.3, pp.379-391, 1987.
[10] Dekker, M., Karel., V. D. and Pim, O., “How to Use Aggregation and Combined Forecasting to Improve Seasonal Demand Forecasts”, International Journal of Production Economics, Vol.90, No.2, pp.151-167, 2004.
[11] Dunn, D. M., Williams, W. H. and DeChaine, T. L., “Aggregate versus Subaggregate Models in Local Area Forecasting”, Journal of the American Statistical Association, Vol.71, No.1, pp.68-71, 1976.
[12] Edwards, J. B. and Orcutt, G. H., “Should Aggregation prior to Estimation be the Rule? ”, Review of Economics and Statistics, Vol.51, No. 4, pp.409-420, 1969.
[13] Fliedner, E. B. and Mabert, V. A., “Constrained Forecasting: Some Implementation Guidelines”, Decision Sciences, Vol. 23, No. 5, pp. 1143-1161,1992.
[14] Fliedner, E. “ A Comparative Analysis of Hierarchical Forecasting System Strategies with a Traditional Forecasting Methodology”, Unpuplished Doctoral Dissertation, Indiana University.
[15] Fliedner, E. B. and Lawrence, B., “Forecasting System Parent Group Formulation: an Empirical Application of Cluster Analysis”, Journal of Operations Management, Vol.12, No.2, pp.119-130, 1995.
[16] Fliedner, G., “An Investigation of Aggregate Variable Time Series Forecast Strategies with Specific Subaggregate Time Series Statistical Correlation”, Computer and Operations Research, Vol.26, No.11, pp.1133-1149, 1999.
[17] Fliedner, G., “Hierarchical Forecasting: Issues and Use Guidelines”, Industrial Management and Data Systems, Vol.101, No.1, pp.5-12, 2001.
[18]Fogarty, D. W. and Hoffman, T. R., “Production and Inventory Management”,
Cincinnati: South-Western, 1984.
[19] ranses, P. H., “Fitting a Gompertz Curve”, The Journal of Operation Research Society, Vol.45, No.1, pp.109-113, 1994.
[20] Garg, M. L., Rao, B. R. and Redmond, C. K., “Maximum-Likelihood Estimation of the Parameters of the Gompertz Survival Function”, Applied Statistics, Vol.19, No.2, pp.152-159, 1970.
[21] Geestenkorn, T., “Estimation of a Parameter of the Logistic Distribution”, Transactions of the Eleventh Prague Conference on Information Theory, Statistical Decision Functions, Random Processes, Prague: Academia Publishing House of the Czechoslovak Academy of Sciences, pp.441-448, 1980.
[22] Gompertz, B., “On the Nature of the Function Expressive of the Law of Human Mortality and on the New Mode of Determining the Value of Life Contingencies”, Philosophical Transactions of Royal Society A, Vol.115, pp.513-580, 1825.
[23] Gross, C.W. and Sohl, J. E., “Disaggregation Methods to Expedite Product Line Forecasting.”, Journal of Forecasting, Vol.9, No.3, pp.253–254, 1990.
[24] Gruber, H. and Verboven, H., “The Diffusion of Mobile Telecommunication Services in the European Union”, European Economic Review, Vol.45, No.3, pp.577-588, 2001.
[25] Grunfeld, Y. and Griliches, Z., “Is Aggregation Necessarily Bad?”, Review of Economics and Statistics, Vol.42, No1, pp.1–13, 1960.
[26] Harvey, A.C., “Time Series Forecasting Based on the Logistic Curve”, Journal of the Operation Research Society, Vol.35, No.7, pp.641-646, 1984.
[27] Ilmakunnas, P., “Aggregation vs. Disaggregation in Forecasting Construction Activity”, In: Barker, T.S., Pesaran,H. (Eds.), 1990.
[28] Kahn, K.B., “Revisiting Top-Down versus Bottom-Up Forecasting.”, Journal of Business Forecasting (Summer), pp.14–19, 1998
[29] Kinney, W. R. Jr., “Predicting Earnings: Entity vs. Sub-entity Data”, Journal of Accounting Research, Vol.9, No.1, pp.127-136, 1971.
[30] Lapide, L., “New Developments in Business Forecasting.”, Journal of Business Forecasting (Summer), pp.28–29, 1998.
[31] Leach, D., “Re-evaluation of the Logistic Curve for Human Populations”, Journal of the Royal Statistical Society,Series A, pp.94-103, 1981.
[32] Levenhach, H. and Cleary, J. P., “Forecasting : Practice and Process for Demand Management”, Thomson, Duxbury, Belmont, 2006.
[33] Levi, D. S., “Kaminsky, P., and Levi, E. S., “Designing and Managing the Supply Chain”, The McGraw-Hill Companies Inc, 2000.
[34] Lutkepohl, H., “Forecasting Contemporaneously Aggregated Vector ARMA Processes”, Journal of Business and Economic Statistics, Vol.2, No.3, pp.201-214, 1984.
[35] Mahajan, V., Muller, E. and Bass, F.M., “New Product Diffusion Models in Marketing: A Review and Directions for Research”, Journal of Marketing, Vol.54, No.1. pp.1-26, 1990.
[36] McLeavey, D. W. and Narasimhan, S. L., “Production and Inventory Control”,Newton: Allyn and Bacon, 1985.
[37] Meade, N., “The Use of Growth Curves in Forecasting Market Development-A Review and Appraisal”, Journal of Forecasting, Vol.3, No.4, pp.429-451, 1984.
[38] Meade, N., “A Modified Logistic Model Applied to Human Populations”, Journal of the Royal Statistical Society, Series A, Vol.151, No.3, pp.491-498, 1988.
[39] Meade, N. and Islam, T., “Forecasting with Growth Curves: an Empirical Comparison”, International Journal of Forecasting, Vol.11, No2, pp.199-215, 1995.
[40] Meade, N. and Islam, T., “Technological Forecasting-Model Selection, Model Stability, and Combining Models”, Management Science, Vol.44, No.8, pp.1115-1130, 1998
[41] Miller, J.G., Berry, W. and Lai, C.-Y.F., “A Comparison of Alternative Forecasting Strategies for Multi-stage Production Inventory Systems.” Decision Sciences, Vol.7, No.4, pp.714–724, 1976.
[42] Mohamed, Z. and Bodger, P., “A Comparison of Logistic and Harvey Models for Electricity Consumption in New Zealand”, Technological Forecasting and Social Change, Vol.72, No.8, pp.1030-1043, 2005.
[43] Muir, J.W., “The Pyramid Principle”, Proceedings of 22nd Annual Conference,
American Production and Inventory Control Society, pp.105-107, 1979.
[44] Orcutt, G., Watts, H.W. and Edwards, J.B., “Data Aggregation and Information Loss.” American Economic Review, Vol.58, No 4, pp.773–787, 1968.
[45] Plossl, G. W., “Getting the Most from Forecasts”, Production and Inventory Management, Vol.14, No.1, pp.1-16, 1973.
[46] Punj, G. N., Stewart, D. W. and Furse, D. H., “A Typology of Individual Search
Strategies Among Purchasers of New Automobile”, Journal of Consumer Research, Vol.10, No.4, pp.417-431, 1984.
[47] Schmittlein, D. C. and Mahajan, V., “Maximum Likelihood Estimation for an Innovation Diffusion Model of New Product Acceptance”, Marketing Science, Vol.1, No.1, pp.57-58, 1982.
[48] Schwarzkoph, A.B., Tersine, R.J. and Morris, J.S., “Top-Down versus Bottom-Up Forecasting Strategies.”, International Journal of Production Research, Vol.26, No.11, pp.1833–1843, 1988.
[49] Shlifer, E. and Wolff, R. W., “Aggregation and Proration in Forecasting”, Management Science, Vol.25, No.6, pp.594-603, 1979.
[50] Stadtler, H. and Kilger, C., “Supply Chain Management and Advanced Planning”, Springer, 2005.
[51] Stoner, P. M., “Fitting the Exponential Function and the Gompertz Function by the Method of Least Squares”, Journal of the American Statistical Association, Vol.36, No.216, pp.515-518, 1941.
[52] Srinivasan, V. and Mason, C. H., “Nonlinear Least Squares Estimation of New Product Diffusion Models”, Marketing Science, Vol.5, No.2, pp.169-178, 1986.
[53] Theil, H., “Linear Aggregation of Economic Relations”, Amsterdam: North-Holland, 1954.
[54] Tsoularis, A. and Wallance, J., “Analysis of Logistic Growth Models”, Mathematical Biosciences, Vol.179, No.1, pp.21-25, 2002.
[55] Weatherford, L.R., Kimes, S.E. and Scott, D.A., “Forecasting for Hotel Revenue Management: Testing Aggregation against Disaggregation.”, Cornell Hotel and Restaurant Administration Quarterly (August), pp53–64, 2001.
[56] Venkatesan, R. and Kumar, V., “A Genetic Algorithms Approach to Growth Phase Forecasting of Wireless Subscribers”, International Journal of Forecasting, Vol.18, No.4, pp.625-646, 2002.
[57] Verhust, P. F., “Notice Sur La Loi Que La Population Suit Dans Son Accroissement”, Curr. Math. Phys., Vol.10, pp.113, 1838.
[58] Wang, F. K., “A Hybrid Approach to Estimate the Parameters of the Diffusion Model”, 24th International Symposium on Forecasting, 2004.
[59] Wei, W. W. S. and Bovas, A., “Forecasting Contemporal Time Series Aggregates”, Communications in Statistics, Vol. 10, No.13, pp. 1335-1344, 1981.
[60] Wheelwright, S.C. and Makridakis, S., “ Examination of the Use of Adpative Filtering in Forecasting.”, Operational Research Quarterly, Vol.24, No.1, pp.55-64, 1973.
[61] Wilson, J. H. and Keating, B., “Business Forecasting”, McGraw-Hill Companies Inc, 2002.
[62] Winsor, C. P., “The Gompertz Curve as a Growth Curve”, Proceeding of the National Academy of Sciences of the United States of America”, Vol.18, No.1, pp.1-8, 1932.
[63] Withycombe, R., “Forecasting with Combined Seasonal indices”, International Journal of Forecasting, Vol.5, No.4, pp.547-552, 1989.
[64] Zellner, A., “On the Aggregation Problem: A New Approach to a Troublesome Problem”, in: K.A. Fox et al., eds., Economic Models, Estimation, Programming, New York: Springer-Verlag, pp.365-374, 1969.
[65] Zellner, A. and Tobias, J., “A Note on Aggregation, Disaggregation and forecasting performance.”, Journal of Forecasting, Vol.19, No.5, pp.457–469, 2000.
[66] Zotteri, G., Kalchschmidt, M. and Caniato, F., “The Impact of Aggregation Level on Forecasting Performance.”, International Journal of Production Economics, Vol.93-94, No.1, pp.479-491, 2005.