本研究運用Gonzalez, Terasvirta and van Dijk (2004, 2005)所發展的縱橫門檻平滑移轉迴歸模型，以異質(heterogeneity)角度探討在大小不同的公司資產規模下，廣告費用之對於企業價值所可能產生的非線性影響變化關係。   
研究首先實證推論，無論以ROA或ROE作為企業價值的代裡變數，所驗證之模型皆為非線性且存在一個結構性變化。而分別就ROA及ROE模型所得轉換門檻值為新台幣64.661億及8.690億，轉換速度則分別為0.2042及0.2075，兩模型之轉換門檻值差異較大，轉換速度則皆為極其平緩的平滑移轉現象。   
先針對ROA模型進行分析，研究結果得到，在資產總額門檻值上下，廣告費用對於ROA，無論門檻上下皆無顯著影響；現金持有則對ROA於門檻值上下皆呈現正向影響，惟此正向關係明顯於大於門檻值時有減弱趨勢；資產總額對ROA之影響，於門檻值上下由負向轉為正向影響；至於，負債總額對ROA之影響，於門檻值上下則相反的由正向轉為負向影響。   
另外，針對ROE進行實證之結果顯示，在資產總額門檻值上下，廣告費用對ROE之影響由正向轉為負向影響；現金持有對於ROE無論門檻上下皆無顯著影響；資產總額對ROE之影響，於門檻值上下由負向轉為正向影響；最後，負債總額對於ROE之影響，於門檻值上下則由正向轉為負向影響。   
本研究最主要在探討在不同公司資產規模下，廣告費用之對於企業價值所可能產生的非線性影響。研究所得結果為：就ROA模型而言，在資產總額無論在門檻值上下，廣告費用對ROA皆無顯著影響；然而，針對ROE進行實證之結果則顯示，在資產總額大於門檻值之8.690億時，廣告費用對ROE有正向影響，小於門檻值時，廣告費用則對ROE轉為負向影響關係。

This research employs the panel threshold smooth transition regression model elaborated by Gonzalez, Terasvirta and van Dijk (2004, 2005) to investigate the effect of advertising on firm value under the different levels of asset size from the view of non-linear heterogeneity.

The empirical findings first indicate that there exists one structural change no matter for models of using ROA or ROE as the proxy for the firm value. The threshold values and the speeds of transition are 6.4661 billion NT dollars and 0.2042 for ROA model and 0.8690 billion NT dollars and 0.2075 for ROE model, respectively. As shown from the empirical results, there is a big difference between ROA and ROE models in the value of thresholds, however, the speeds of transition are quite similar for both models.

Analyzing the ROA model, the result shows that the advertising does not has any effect on firm value for all ranges of firm assets. For other explanation variables, cash holding shows diminishing positive effect on ROA. Total asset and total debt show the effects turn from negative to positive and from positive to negative on ROA, respectively, when total asset is from upper region to lower region.  

Regarding the model of ROE, the result shows the effect of advertising on firm value turns from positive to negative for asset from upper region to lower region. Cash holding shows no effect on firm value. Moreover, same results as ROA model are found for the effect of total asset and total debt on ROE.

The main purpose of this research is using firm assets as threshold to investigate the non-linear effect of advertising on firm values. For ROA proxy model, the result shows that the advertising does not has any effect on firm value for all ranges of firm assets. On the other hand, the ROE proxy model shows the effect of advertising on firm value turns from positive to negative for asset from upper region to lower region.

致謝辭…………………………………………………………………	i
中文摘要………………………………………………………………	ii
英文摘要………………………………………………………………	iii
目錄…………………………………………………………………… v
圖目錄…………………………………………………………………	vii
表目錄…………………………………………………………………	viii
第壹章 緒論……………………………………………………………	1
第一節 研究背景與動機……………………………………………	1
第二節 研究目的……………………………………………………	4
第三節 研究架構…………………………………………………	6
第貳章 文獻探討………………………………………………………	7
第一節 廣告之定義與功能…………………………………………	7
第二節 廣告支出的會計處理準則…………………………………	8
第三節 相關實證研究………………………………………………	8
第參章 研究方法………………………………………………………	15
第一節 縱橫單根檢定………………………………………………	15
第二節 縱橫平滑移轉迴歸模型……………………………………	18
第三節 縱橫平滑移轉迴歸模型之設定……………………………	23
第肆章 實證結果與分析………………………………………………	28
第一節 資料說明……………………………………………………	28
第二節 縱橫單根檢定結果…………………………………………	29
第三節 縱橫平滑移轉檢定結果……………………………………	30
第伍章 結論與建議……………………………………………………	39
結論…………………………………………………………………	39
參考文獻………………………………………………………………	42

圖 目 錄
圖1-3-1流程架構………………………………………………………	6
圖 3-3-1 m=1之平滑移轉轉換模型…………………………………	21
圖 3-3-2 m=2之平滑移轉轉換模型…………………………………	22
圖4-3-1 ROA之轉換函數圖形…………………………………………	38
圖4-3-2 ROE之轉換函數圖形…………………………………………	38

表目錄
	頁次
表1-1-1：台灣推動IFRSs架構之工作計劃時程表		3
表4-1-1：各變數基本敘述統計量		29
表4-2-1：各變數之縱橫單根檢定結果		30
表4-3-1  資產總額對ROA之同質性檢定		31
表4-3-2  資產總額對ROA之轉換區間個數檢定		31
表4-3-3  資產總額對ROA之模型估計數據		32
表4-3-4  資產總額對ROA模型之影響		32
表4-3-5  資產總額對ROE之同質性檢定		34
表4-3-6  資產總額對ROE轉換區間個數檢定		34
表4-3-7  資產總額對ROE之模型估計數據		36
表4-3-8  資產總額對ROE模型之影響		36

中文部分
1.	林敬穎，2009，研究發展支出與廣告支出對於企業價值攸關性之探討：以台灣公司為例，碩士論文，國立成功大學會計學研究所。
2.	徐君毅，2001，研發與廣告支出與企業價值變動之因果關係研究，碩士論文，東海大學企業管理學研究所。
3.	許戍，2002，研究發展、廣告支出與企業經營績效關聯性之研究，碩士論文，國立政治大學會計學研究所。
4.	溫士賢，2003，研發、廣告與人力支出和企業價值關聯性之探討，碩士論文，國立台灣大學會計學研究所。
5.	蔡宗仁，1995，廣告支出會計理論與問題之研究，碩士論文，國立政治大學會計學研究所。
6.	謝月香，2000，無形資產，碩士論文，國立成功大學會計學研究所。
7.	謝佳樺，2005，研發和廣告支出與未來經濟效益相關性的實證研究：以台灣公司為例，碩士論文，國立成功大學會計學研究所。

英文部分
1.	Andrews, D. W. K. and W. Ploberger, 1994. Optimal tests when a nuisance parameter is present only under the alternative, Econometrica, 62, 1383.
2.	Bublitz, B. and M. Ettredge, 1989. The information in discretionary outlays: Advertising, research and development, The Accounting Review, 64, 108-124.
3.	Chauvin, K. W. and M. Hirschey,1993. Advertising , R & D Expenditures and the Market Value of the Firm, Financial Management, 22, 128-140. 
4.	Choi, J., 1994. The effect of advertising and R&D expenditures on the firm value: An empirical analysis by Tobin’s Q, Korean Accounting Review, 19, 103-124.
5.	Davies, R. B., 1977. Hypothesis testing when a nuisance parameter is present only under the alternative, Biometrika, 64, 247.
6.	Gonzalez, A., T. Terasvirta and D. van Dijk, 2004. Panel Smooth Transition Regression Model and an Application to Investment Under Credit Constraints, Working papers. 
7.	Gonzalez, A., T. Terasvirta and D. Van Dijk, 2005. Panel Smooth Transition Regression Models, Working papers.
8.	Granger, C. W. J. and T. Terasvirta, 1993. Modelling Nonlinear Economic Relationships, Oxford University Press.
9.	Han, B. H. and D. Manry, 2004. The value-relevance of R & D and advertising expenditures: Evidence from Korea, The International Journal of Accounting, 39, 155–173. 
10.	Hansen, B. E., 1996. Inference when a nuisance parameter is not identified under the null hypothesis, Econometrica, 64, 413.
11.	Hansen, B. E., 1999. Threshold Effects in Non-dynamic Panels: Estimation, Testing, and Inference, Journal of Econometrics, 93, 345-368.
12.	Hirschey, M. and J. J. Weygandt, 1985. Amortization policy for advertising and research and development expenditures, Journal of Accounting Research, 23, 326– 335.
13.	Ho, Y. K., H. T. Keh and J. M. Ong, 2005. The Effects of R&D and Advertising on Firm Value: An Examination of Manufacturing and Nonmanufacturing Firms, IEEE Transactions on Engineering Management, 52, 3-14. 
14.	Im, K. S., M. H. Pesaran and Y. Shin, 2003. Testing for Unit Roots in Heterogeneous Panels, Journal of Econometrics, 115, 53–74.
15.	Jansen, E. S. and T. Terasvirta, 1996. Testing Parameter Constancy and Super Exogeneity in Econometric Equations, Oxford Bulletin of Economics and Statistics, 58, 735–763.
16.	Levin, A. and C. F. Lin, 1992. Unit Root Tests in Panel Data: Asymptotic and Finite-sample Properties, University of California, San Diego. 
17.	Levin, A., C. F. Lin and C. S. J. Chu, 2002. Unit Root Tests in Panel Data: Asymptotic and Finite-sample Properties, Journal of Econometrics, 108, 1-24. 
18.	Lundbergh, S., T. Terasvirta and D. V. Dijk, 2003. Time-varying Smooth Transition Autoregressive Models, Journal of Business and Economic Statistics, 21, 104–121.
19.	Luukkonen, R., P. Saikkonen and T. Terasvirta, 1988. Testing Linearity Against Smooth Transition Autoregressive Models, Biometrika, 75, 491–499.
20.	Maddala, G. S. and S. Wu, 1999. A comparative study of unit root tests with panel dataand a new simple test, Oxford Bulletin of Economics and Statistics, 61, 631-652.
21.	Ohlson, J., 1995. Earnings, book values, and dividends in equity valuation, Contemporary Accounting Research, 11, 661– 687. 
22.	Shah, S. Z. A., A. W. Stark and S. Akbar, 2009. The value relevance of major media advertising expenditures: Some U.K. evidence, The International Journal of Accounting, 44, 187-206. 
23.	Terasvirta, T., 1994. Specification, Estimation and Evaluation of Smooth Transition Autoregressive Models, Journal of the American Statistical Association, 89, 208–218.
24.	Terasvirta, T., 1998. Modelling Economic Relationships with Smooth Transition Regressions, in Handbook of Applied Economic Statistics, ed. by A. Ullah and D. E. A. Giles, 507–552. New York: Marcel Dekker.