廠商行為假設與技術無效率的估計問題

機構典藏 > College of Business and Management > Graduate Institute & Department of Economics > Research Paper > Item 987654321/46907

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/46907

Title:	廠商行為假設與技術無效率的估計問題
Other Titles:	Behavioral Assumptions and Technical Inefficiency Estimation
Authors:	陳怡宜
Contributors:	淡江大學經濟學系
Keywords:	隨機邊界模型;技術無效率;成本函數;利潤函數;stochastic frontier models;technical inefficiency;cost function;profit
Date:	2009
Issue Date:	2010-04-15 15:33:28 (UTC+8)
Abstract:	這項研究計畫的主題，在於探討隨機邊界模型中技術無效率的估計，是否會因為對於廠商行為假設的誤設，而影響估計結果。在相關文獻中，廠商行為假設的選擇，常是依賴可得資料而定。例如，雖然大多數廠商理論皆認為廠商最可能的生產行為是追求利潤極大，但若產出價格不可得，則無法估計利潤函數，因此研究人員便常假設廠商行為為成本極小化，而以成本函數估計之。錯誤的行為假設，對估計結果有一定影響。從計量模型的角度來看，成本模型假設產量為外生，而利潤模型則假設產量為內生，而這種內外生變數的區別，將影響模型的估計結果。在此研究計畫中，我們將以蒙地卡羅模擬的方式，探討廠商行為假設誤設，對技術無效率估計值的影響。我們先假設廠商為極大利潤者，以之產生模擬變數，再以成本函數估計之，比較估計結果；我們亦將假設廠商為成本極小化者，而觀察當我們以利潤函數估計時，造成的錯誤。在模擬中，我們強調以對偶理論，將生產函數中的技術無效率，帶入成本函數及利潤函數中（而非以ad hoc 的方式假設成本無效率及利潤無效率的存在），因此兩個函數中的無效率來源明確、一致，有利於比較。此外，我們採用Kumbhakar and Wang (2006)的模型估計成本及利潤行為參數；該方法可以避免利潤為負、無法取對數的問題。 In this research proposal, we intend to investigate the effects on technical inefficiency estimate as a consequence of incorrect behavioral assumptions on firms. In the literature of stochastic frontier applications, researchers often choose the behavioral assumption by convenience. For instance, if the output price is not available, researchers often resort to cost minimization assumption even though profit maximization is likely to be the most plausible behavior of firms. Incorrect behavioral assumptions would cause bias to the estimates of firm behaviors, including that of technical inefficiency. From the econometrics point of view, output is exogenous to cost minimization and endogenous to profit maximization. A false assumption biases the estimation. In this research, we will use Monte Carlo simulations to investigate the consequences of incorrect assumptions. We will generate data consistent with profit maximization, and estimate the data using cost frontier and compare the results. We will also generate data consistent with cost minimization and estimate it by profit frontier. We use the model of Kumbhakar and Wang (2006) to generate/estimate data. The primal-based approach has several advantages in the estimation.
Appears in Collections:	[Graduate Institute & Department of Economics] Research Paper

Files in This Item:

There are no files associated with this item.

Loading...