本文使用門檻模型來探討經濟成長率和失業率之間的非線性關係。本文模型最主要的創新是考慮了內生的解釋變數和門檻變數。實證結果指出歐肯法則為非線性，
並且在不同模型之下大致上支持歐肯係數絕對值在景氣收縮階段大於其在景氣擴張階段。

This paper apply a threshold model to examine the nonlinear relationship between economic growth and unemployment rate. The key innovation of our model is that it takes into account endogenous explanatory variables and endogenous threshold variables. Empirical results show that Okun’s law is nonlinear. Among different models under consideration,the absolute value of Okun’s coefficient during contraction period is larger than that during expansion period.

目錄
第一章 緒論........................................................ 1
第一節 研究動機與目的 ............................................ 1
第二節 本文架構 .................................................. 3
第二章 文獻回顧.................................................... 4
第三章 研究方法................................................... 10
第一節 單根檢定 ................................................. 10
第二節 內生性檢定 ............................................... 13
第三節 門檻模型 ................................................. 14
第四節 模型非線性檢定........................................... 18
第四章 實證結果與分析............................................. 19
第一節 模型的設立 ............................................... 19
第二節 資料的來源與處理 ......................................... 22
第三節 實證結果分析 ............................................. 23
第五章 結論....................................................... 36
參考文獻........................................................... 37
附錄............................................................... 40
附表
(表一).原始資料單根檢定 ........................................ 24
(表二) .差分變數資料單根檢定 ................................... 24
(表三).缺口變數資料單根檢定 .................................... 25
(表四)內生性檢定結果............................................ 25
(表五).以產出成長為內生門檻變數的估計結果 ....................... 28
(表六).以失業率變動為內生門檻變數的估計結果 .................... 29
(表七).以景氣領先指標季增率為內生門檻變數的估計結果............. 30
(表八).以景氣領先指標年增率為內生門檻變數的估計結果............. 31
(表九)以景氣同時指標季增率為內生門檻變數的估計結果.............. 32
(表十).以景氣同時指標年增率為內生門檻變數的估計結果............. 33
(表十一).以景氣領先指標季增率為外生門檻變數的估計結果 ........... 34
(表十二).以景氣領先指標年增率為外生門檻變數的估計結果........... 35
附圖............................................................... 40

參考文獻
中文參考文獻：
[1] 田慧琦( 2010 )，“台灣失業率和產出之關聯及可能影響因素探討–歐肯法則
( Okun’s Law ) 實證分析”，中央銀行季刊，第 32 卷第 3 期。
[2] 江靜儀 ( 2006 )，“歐肯法則( Okun’s Law )－台灣實證研究”，中央研究院經
濟研究所，《經濟論文》，第 34 卷第 3 期，355－389。
[3] 萬哲鈺、高崇瑋 (2008)，“不對稱歐肯法則之台灣實證”，中央研究院經濟研
究所，《台灣經濟預測與政策》，第 39 卷第 1 期，1－31。
英文參考文獻：
[1] Alting, D., T. Fitzgerald,and P. Rupert(1997),“Okun’s Law Revisited:Should We
Worry about Low Unemployment?”Federal Reserve Bank of Cleveland Economic
Commentary,15,1－4.
[2] Caner, M. and B. Hansen. (2004),“Instrumental Variable Estimation of a Thresho-
ld Model,” Econometric Theory, 20, p. 813-843.
[3] Courtney, H.G. (1991),“The Beveride Curve and Okun’s Law:“A Re-Examination
of Fundamental Relationships in the United States ”,Ph.D.Dissertation,Massachu-
ssetts Institute of Technology.
[4] Cuaresma, J.C. (2003) ,“Okun’s Law Revisited”,Oxford Bulletin of Economics
and Statistics,65(4),439-451.
[5] Dickey, D. A. and W. A. Fuller, (1979),“Distribution of the estimatetors for a-
Utoregressive Time Series with a Unit Root” Journal of the American Statistcail
Association.
[6] Elliott, G., T.J. Rothenberg, and J.H. Stock (1996), “Efficient Test for an Autore-
gressive Unit Root”, Econometrics, vol. 64, 813-836.
[7] Evans, G.W. (1989) , “Output and Unemployment Dynamics in the United States:
1950–1985,”Journal of Applied Econometrics, 4, 213–237. 38

[8] Freeman, D. G. (2001),“Panel Tests of Okun’s Law for Ten Industrial Countries,”
Economic Inquiry, 39, 511–523.
[9] Friedman, B. M. (1988) , “Lessons on Monetary Policy from the 1980s,” Journal
of Economic Perspectives, 2, 21–72.
[10] Gordon, R. J.(1984),“Unemployment and Potential Output in the1980s, ”Brooki-
ngs Papers on Economic Activity,15,537–564.
[11] Granger, C. W. J. and P. Newbold(1974),“Spurious regressions in econometric-
s,” Journal of Econometrics, 2, 111-120.
[12] Hansen, B. E. (1996) , “Inference when a Nuisance Parameter is not Identified
under the Null Hypothesis,” Econometrica,64(2),413–430.
[13] Hansen, B. E. (2000),“Sample Splitting and Threshol Estimation,”Econometrica,
68(3), 575–603.
[14] Knotek, E. S. II (2007),"How Useful Is Okun's Law?" Economic Review, Federal
Reserve Bank of Kansas City,4,73-103.
[15]Kourtellos, A., T. Stengos, and C. M. Tan,.(2007), “THRET: Threshold Regressi-
on with Endogenous Threshold Variables”, Working Papers, 2008, ,C13,C51,
JEL Classifications.
[16] Lee, J. (2000) “The Robustness of Okun’s Law: Evidence from OEC Countries,”
Journal of Macroeconomics, 22(2), 331–356.
[17] Malley, J. and H. Molana (2008),"Output,unemployment and Okun's law: Some
evidence from the G7",Economics Letters,Nov.,113-115.
[18] Moosa, I. A (1997),“A cross-country comparison of Okun.s coefficient.”Compa-
rative Economics,24,3,June.
[19] Neftci, S. N. (1984),“Are Economic Time Series Asymmetric over the Business
Cycle?”Journal of Political Economy,92,307–335.
[20] Okun, A. M. (1962), “Potential GNP: its measurement and significance,” Proce- edings of the Business and Economic Statistics Section of the American Statisti-
cal Association, Alexandria, VA: American Statistical Association 98-104.
[21] Palley, T. I. (1993),“Okun’s Law and the Asymmetric and the Changing Cyclical
Behaviour of the USA Economy,” International Review of Applied Economics,
7(2),144–162.
[22] Perman R. and C. Tavera (2005), “A cross-country analysis of the Okun’s Law
coefficient convergence in Europe.,Applied Economics, 37,21,Dec., 2501 - 2513.
[23] Phillips, P. C. and P. Perron (1988), “Testing for a unit root in time series regres-
sion,”Biometrika, 75, 335-346.
[24]Sichel, D. E. (1993) , “Business Cycle Asymmetry: A Deeper Look,” Economic
Inquiry, 31,224–236.
[25] Schnabel, G. (2002) , “Output trends and Okun's law”, BIS Working Paper, 111,
April.
[26] Vir′en,M. (2001), “The Okun Curve is Non-Linear,” Economics Letters, 70,2,
253-257