臺灣博碩士論文加值系統

由於營利事業所得稅是國家主要的稅源之一，且該稅之查核係採選案查核而非普查，在查審人力無法增加的限制下，如何從事該稅逃漏之有效查緝值得深入探究！本研究透過22項財務比率差異與比值，組合類神經網路、因素分析及羅吉斯迴歸等三種計量方法，提出五種預測模式，並進行預測效果之實證比較。我們以財政部台灣省北區國稅局轄區內的電子資訊產業及其八十六及八十七年稅務資料為例，利用複式抽樣法及重複測度分析，透過型一歸類錯誤率 (係反映未能偵測實際逃漏稅之風險)、型二歸類錯誤率 (係反映查緝實際未逃漏稅之風險) 及整體歸類錯誤率 (係反映型一及型二之綜合風險) 三項指標評估五種預測模式之效果。研究結果顯示，直接以 22 項財務變數納入類神經網路模式中之預測效果最佳，但卻無法獲悉具顯著預測能力之財務變數。除預測效果外，協助查審人員設定查緝方向亦是訴求重點，基於此一觀點，並根據研究結果，我們提供了一些實務上的應用建議。

Business income tax evasion has been a very popular and serious problem. A direct way to reduce tax evasion is to enhance auditing. Owing to limited resources, it seems hard to increase auditors. Therefore, how to effectively predict if a tax evasion will occur becomes important. The purpose of this study is to conduct comparisons of performance among different prediction approaches, and then find out the most effective one.
Five prediction approaches by means of neural networks, factor analysis and logistic regression are used. They are based on 22 financial variables. The overall prediction error rate, Type I prediction error rate, and Type II prediction error rate serve as prediction performance criteria. Using Bootstrapping sampling and repeated measures analysis, the approach of neural network based on 22 financial variables was found to be the most effective. However, variables possessing explanatory power cannot be identified by the approach. Factor analysis on 22 financial variables, followed by stepwise logistic regression, is suggested to help with critical variable selection.

目 錄
中文提要 ……………………………………………………………… i
英文提要 ……………………………………………………………… ii
誌謝 ……………………………………………………………… iii
目錄 ……………………………………………………………… iv
表目錄 ……………………………………………………………… vi
圖目錄 ……………………………………………………………… vii
一、 緒論………………………………………………………… 1
1.1 研究動機……………………………………………………… 1
1.2 研究目的……………………………………………………… 2
1.3 研究範圍……………………………………………………… 3
二、 文獻回顧與評述……………………………………………… 4
2.1 稅務稽核相關資料…………………………………………… 4
2.2 租稅逃漏行為與租稅查核…………………………………… 6
2.3 統計模式……………………………………………………… 7
2.4 類神經網路介紹……………………………………………… 12
2.4.1 類神經網路簡介……………………………………………… 12
2.4.2 基本原理概述………………………………………………… 13
2.4.3 網路模式分類………………………………………………… 14
2.4.4 倒傳遞演算法則……………………………………………… 17
三、 研究設計……………………………………………………… 21
3.1 研究對象及樣本……………………………………………… 21
3.2 研究步驟……………………………………………………… 21
3.3 研究變數……………………………………………………… 23
3.4 預測方法……………………………………………………… 24
四、 實證分析……………………………………………………… 27
4.1 因素分析……………………………………………………… 27
4.2 逐步二元羅吉斯迴歸………………………………………… 30
4.3 二元羅吉斯迴歸……………………………………………… 32
4.4 類神經網路…………………………………………………… 34
4.5 重複測度分析………………………………………………… 37
五、 結論與建議…………………………………………………… 42
5.1 結論與建議…………………………………………………… 42
5.2 研究限制……………………………………………………… 43
5.3 後續研究建議………………………………………………… 44
參考文獻 ………………………………………………………………… 46
附錄一 操作相關程式………………………………………………… 48
附錄二 訓練資料集(1)因素得點……………………………………… 53
附錄三 方法A(樣本11)歸類結果…………………………………… 63
附錄四 五種方法整體歸類錯誤率…………………………………… 73
附錄五 五種方法型一歸類錯誤率統計表…………………………… 76
附錄六 五種方法型二歸類錯誤率統計表…………………………… 78

1. 財政部賦稅署 (1993)，營利事業所得稅查核技術之研究。
2. 高雄市國稅局 (1994)，從營利所得稅逃漏型態論行政罰法之改進。
3. 胡秀杏，營利事業所得稅逃漏行為之研究，台灣大學商研所碩士論文，民國七十六年。
4. 陳順宇，多變量分析，華泰書局，民國八十七年。
5. 葉怡成 (1999)，應用類神經網路，儒林書局，台北。
6. 盧欽滄 (1994)，稅務調查與間接證明法兼論租稅詐欺，凱侖出版社，台北。
7. 蘇木春、張孝德 (2000)，機器學習：類神經網路、模糊數學及基因演算法則，全華科技圖書公司，台北。
8. 蘇碧霞 (1991)，租稅違章逃漏查緝之研究，七十八年度公教人員出國專題研究報告。
9. Altman, E. (1993), Corporate Financial Distress and Bankruptcy, John Wiley & Sons, New York.
10. Bentz, Y. and D. Merunka (2000), “Neural networks and the multinomial logit for brand choice modeling: a hybrid approach,” Journal of Forecasting, 19, pp. 177-200.
11. Chu, C. Y. and L. Tan (1996), “Tax evasion by small business: theory and empirical evidence of Taiwan,” Public Economic Review, 1, pp. 157-183.
12. Haykin, S. (1999), Neural Network: A Comprehensive Foundation, Second Edition, Prentice Hall, Englewood Cliffs, NJ.
13. Hunter, W. J. and M. A. Nelson (1996), “An IRS production function,” National Tax Journal, 49, pp. 105-115.
14. Johnson R. A. and D. W. Wichern (1998), Applied Multivariate Statistical Analysis, Fourth Edition, Prentice Hall, Englewood Cliffs, NJ.
15. Jonathan, R. M., E. Pednault, and M. Sudan (1997), “A statistical perspective on data mining,” Future Generation Computer Systems, 13, pp. 117-134.
16. McKee, T. E. and M. Greenstein (2000), “Predicting bankruptcy using recursive partitioning and a realistically proportioned data set,” Journal of Forecasting, 19, pp. 219-230.
17. Neter, J., M. H. Kutner, C. J. Nachtsheim, and W. Wasserman (1996), Applied Linear Statistical Models, Fourth Edition, IRWIN, Chicago.
18. Ohlson, J. (1980), “Financial ratios and probabilistic prediction of bankruptcy,” Journal of Accounting Research, 18, pp. 109-131.
19. SAS Institute Inc. (1997), SAS/STAT Software: Changes and Enhancements through Release 6.12, SAS Institute Inc., Cary, NC.
20. SPSS Inc. (2002), http://www.spss.com/spssbi/ applications/fraud/index.htm.
21. Sung, T. K., N. Chang, and G. Lee (1999), “Dynamics of modeling in data mining: interpretive approach to bankruptcy prediction,” Journal of Management Information Systems, 16, pp. 63-85.
22. Webley, P., M. Cole, and O. Eidjar ( 2001), “The prediction of self-reported and hypothetical tax-evasion: evidence from England,” France and Norway Journal of Economic Psychology, 22, pp. 141-155.
23. Westphal, C. and T. Blaxton (1998), Data Mining Solutions Methods and Tools for Solving Real-World Problems, John Wiley & Sons, New York.