台灣平版印刷機械業要在瞬息萬變的市場中欲脫穎而出，必須不間斷觀察市場動態，調整改變自己的營運方針，朝企業有利之方向發展。然而二手平版印刷機械業是否能在有限的市場上創造出不同的獲利績效，關鍵在於每部二手平版印刷機成交的獲利率與成交時不同的買賣成交關鍵因素之間，是否存在關聯性。二手平版印刷機業者必須思考，如何從有限的二手機器銷售中升級至為二手機器創造出更高的價值提供者。
二手平版印刷機械產業正面臨過度競爭的困境，為了提升產業競爭力，更應該在二手平版印刷機械銷售過程中，提高二手機器交易的獲利率。同一部二手印刷機，賣給不同的客戶群，可能產生不同的獲利，二手平版印刷機業者如何掌握有效的獲利關鍵因素，以提昇二手平版印刷機的買賣獲利率，才是成功的關鍵。
本研究以南台灣一具規模的二手平版印刷機業者，於2000年至2020年間，成功交易的二手平版印刷機買賣資料及數據，做為研究資料；逐步蒐集每筆成交之各項數據及成交時的各項條件，包括市場、環境條件及機器條件等，有可能影響獲利率的關鍵因素；透過資料整理分類，以逐步迴歸分析，找出影響獲利率顯著的關鍵因素。
研究結果顯示結論如下：
（1）二手機機齡愈高、有中間商、色座單位數1或7、售出時運轉狀況Ａ（可印刷測試），以上條件成立時，該筆交易的獲利率相對較高。
（2）當該二手機是由台灣賣出，則該筆交易的獲利率相對較低。另外也發現交互作用『機齡*買入成本』，顯示當買入成本愈高，機齡愈高反而導致該筆交易獲利率下降。
本研究結果，將可提供二手平版印刷機業者，作為買入決策及賣出定價之參考。

關鍵字：平版印刷機、獲利率、關鍵因素、逐步迴歸。

For offset press industry in Taiwan to excel in the fast-changing world, market dynamic needs to be studied continuously, and to adjust its operational policy therefore striving towards the direction beneficial to the companies. As the duration of service is quite long for the offset press, used offset press has a role in offset press industry. To create good profit n the limited market, decision of buy-in and sell- out of offset press is critical. If companies of used offset press are able to find out the key factors of offset press which might yield better profit, business performance could be greatly increased.
This research applies Stepwise regression model, based on empirical dataset of a representative used offset press company, to explore the critical factors which might affect the profit ratio of used offset press. The process includes: (1) Collect related information of transaction, (2) Data preprocessing, (3) Develop regression model using profit ratio as independent variables, (4) Verify if model matches the three elemental hypothesis of regression: normality, independence and homogeneity of variance, (5) Develop Stepwise regression analysis model, (6) Discuss analysis results and managerial implications.
Our work develops the regression model using the transaction data 2000 to 2020 of a case company. The results show that the used offset press with higher age, dealer engagement, color seats with unit number 1 or 7, operation condition is fine and is able to test printing when sold are key factors. Also, when the used offset press was bought from Taiwan, the profit ratio is relatively low. Besides, the higher the cost of buy-in and the older the age of machine lead to relatively lower profit ratio. The aforementioned results show that Stepwise regression model is suitable for analysis and could assist managers to improve their decision quality of buy-in and sold-out of used offset press companies.

Keywords: used offset press, profit ratio, critical factor, stepwise regression model

中文文獻：
王祿旺，1999，《臺灣區印刷產業發展策略之研究》，台北：五南圖書出版，初版。
林政松，2016，數位印刷技術與鑑定研析，印刷科技季刊，32（4），中央印製廠，　　　　取自https://www.cepp.gov.tw/TheFiles/publication/73457132-af12-4ae6-9961-a6e8555350d4.pdf
張秋英，2019，探討影響合版印刷廠商內部與外部顧客滿意度之研究-兼論交易型與關係型顧客之探討，國立中興大學EMBA碩士學位論文。
張樹棟，1998，中華印刷通史，廣西師範大學出版社。
張樹棟，2010，印刷業典故：何謂印刷。取自http://blog.udn.com/ iink/3727920
賀秋白，2020，印刷的新定義，印刷科技季刊第三十六卷第一期，中央銀行。
羅福林、李興才，1995，印刷工業概論（上），第七版，台北市：中國文化大學出版部，中華學術院印刷工業研究所

英文文獻：
Abolhassani, A., Harner, E. J., & Jaridi, M. (2019). Empirical analysis of productivity enhancement strategies in the North American automotive industry. International Journal of Production Economics, 208, 140-159.
Buer, S.-V., Semini, M., Strandhagen, J. O., & Sgarbossa, F. (2020). The complementary effect of lean manufacturing and digitalisation on operational performance. International Journal of Production Research, 1-17.
Ciurana, J., Quintana, G., & Garcia-Romeu, M. (2008). Estimating the cost of vertical high-speed machining centres, a comparison between multiple regression analysis and the neural networks approach. International Journal of Production Economics, 115(1), 171-178.
Hair, J. F., Black, W. C., & Babin, A. (2010). RE and Tatham, RL (2006), Multivariate Data Analysis. In: Upper Saddle River, NJ: Pearson Prentice Hall.
Loyer, J.-L., Henriques, E., Fontul, M., & Wiseall, S. (2016). Comparison of Machine Learning methods applied to the estimation of manufacturing cost of jet engine components. International Journal of Production Economics, 178, 109-119.
Montgomery, D. C., Peck, E. A., & Vining, G. G. (2012). Introduction to linear regression analysis (Vol. 821): John Wiley & Sons.
Okoshi, C. Y., de Lima, E. P., & Da Costa, S. E. G. (2019). Performance cause and effect studies: Analyzing high performance manufacturing companies. International Journal of Production Economics, 210, 27-41.
Smith, G. (2018). Step away from stepwise. Journal of Big Data, 5(1), 1-12.
Sonoda, S., Takahashi, Y., Kawagishi, K., Nishida, N., & Wakao, S. (2007). Application of stepwise multiple regression to design optimization of electric machine. IEEE transactions on magnetics, 43(4), 1609-1612.
Van Donselaar, K. H., Peters, J., de Jong, A., & Broekmeulen, R. A. (2016). Analysis and forecasting of demand during promotions for perishable items. International Journal of Production Economics, 172, 65-75.
Verlinden, B., Duflou, J., Collin, P., & Cattrysse, D. (2008). Cost estimation for sheet metal parts using multiple regression and artificial neural networks: A case study. International Journal of Production Economics, 111(2), 484-492.
Vlachopoulou, M., Ferryman, T., Zhou, N., & Tong, J. (2013). A stepwise regression method for forecasting net interchange schedule. Paper presented at the 2013 IEEE Power & Energy Society General Meeting.

網路資料：
印刷概論 http://modern.csu.edu.tw/wSite/public/Attachment/f1398761171894.pdf
印刷資訊網 http://www.print.com.tw
生活科技第二冊教師手冊(康和版)
http://163.28.10.78/content/junior/life_tech/tc_jr/student/course/201/201source11.htm
行政院勞工委員會職業訓練局（1998/05/12），行職業資訊研發成果專輯─印刷業。 http://w3.tpsh.tp.edu.tw/organization/shcool/intro1/workinrto/001/002/a091/11.htm
財團法人印刷創新科技研究發展中心　http://www.ptri.org.tw
國家教育研究院　http://terms.naer.edu.tw/detail/1683103/
國發會景氣指標查詢系統　https://index.ndc.gov.tw/n/zh_tw