為了解美國總體經濟指標跟各州領先指數之關聯性，本文使用二元邏輯斯模型檢測美國國家經濟研究局所公布之景氣循環指數，再針對美國50州的領先指標比較，選擇研究數據時間為西元1982年至2013年。根據Stock and Watson的論點確定變數組合，使用動態因子模型和主要元成份分析建立模型，產生同期和領先指標代表目前經濟所呈現的狀態。
	實證結果發現肯塔基州的領先指數無論是使用兩個月或三個月的落後期，對於預測美國總體經濟指標皆有顯著的效果。在比較肯塔基州與美國總體經濟指標時，顯示肯塔基州的預測能力較高。由於美國國家經濟研究局的數據以及國家和州的領先指標對外公布的時間較久，因此無法肯定落後期為一個月時何者的預測能力較優，此外，本文也探討了使用時間頻率為每季或每月兩者的不同之處。最後歸納出影響美國全國經濟的因素在於某些州的經濟活動與全國經濟活動關聯性較大時，較能夠準確預測出未來景氣循環的走向。

In this paper, we seek to study the relation between data on leading indicators and U.S. business cycle by using binary logit model to examine business cycle index of the National Bureau of Economic Research and compare to the leading indicators of the 50 states of the United States. from 1982-2013. According to Stock and Watson’s theory to determine the variable combination. The use of dynamic factor models and principal components to model the current state of the economy has led to a series of coincident and leading indicators. These indicators are specifically designed to help predict the future movements in the state of the economy.

  The empirical result shows Kentucky’s leading index using both of the two or three month lags, the predict ability is significant effect. The conclusion that can be drawn is that two and three months prior, predictions made using the Kentucky leading index will generally be more reliable a predictor for NBER recessions than those using the national leading indicator. One month ahead forecasts are not likely to be very reliable since the NBER number is not available within one month and the state and national leading indicator will not also generally be available so early.

Finally, this paper also discusses the use of time for quarterly or monthly frequency difference between the two. When the state’s economic activity is similar to the country, it can forecast the future direction of the business cycle more accurately.

目錄
目錄 ………………………………………………………………………v
圖目錄 …………………………………………………………………vii
表目錄…………………………………………………………………viii
第一章 緒論………………………………………………………………1
第一節 研究主題…………………………………………………………1
第二節 研究背景與動機…………………………………………………2
第三節 研究目的…………………………………………………………4
第四節 研究限制…………………………………………………………6
第五節 研究架構…………………………………………………………7
第二章 文獻回顧…………………………………………………………8
第一節 景氣循環之不同預測模型探討…………………………………8
壹、國內文獻 ……………………………………………………………8
壹、國外文獻 ……………………………………………………………9
第二節 綜合討論 ………………………………………………………10
第三章 研究方法 ………………………………………………………12
第一節 現代領先指標理論概述 ………………………………………12
第二節 經濟衰退時期的定義 …………………………………………20
第四章 實證結果與分析 ………………………………………………24
第一節 概述 ……………………………………………………………24
第二節 數據資料的考量 ………………………………………………30
第三節 估計結果及分析 ………………………………………………33
壹、 演算美國家家經濟研究局月資料 ………………………………33
貳、 美國50州預測能力分析 …………………………………………36
參、 演算季模型 ………………………………………………………45
第五章 結論與檢討 ……………………………………………………52
參考書目…………………………………………………………………55

圖目錄
圖1-1 領先指標和美國景氣循環圖  ……………………………………5
圖3-1 美國目前的經濟狀態……………………………………………18
圖3-2 兩季度法則和美國國家經濟研究局測量衰退的結果…………20
圖3-3 州領先指數計算及公布時間表…………………………………23
圖4-1 logit模型演算落後2個月正確率百分比(州領先指標)…………42
圖4-2 logit模型演算落後3個月正確率百分比(州領先指標)…………43
圖4-3 預測NBER季資料之兩種預測誤差值  …………………………46
圖4-4 兩季度法則預測衰退之兩種預測誤差值………………………50

表目錄
表3-1 動態單因素模型估計的實證結果………………………………17
表4-1 模型預測矩陣表…………………………………………………28
表4-2 Logit模型演算NBER領先指標結果……………………………34
表4-3 肯塔基州(KY)領先指標演算結果………………………………37
表4-4 威斯康辛州(WI)領先指標演算結 ………………………………40
表4-5 特定logit模型預測能力結果表(落後值為2個月)………………48
表4-6 特定logit模型預測能力結果表(落後值為1季)…………………48

林大超。「台灣與美國兩地景氣循環指標關聯性之研究」。成功大學企管研究所，碩士論文，民國92年。

黃聿銘。「台灣領先指標對景氣循環預測能力的探討」。中央大學經濟研究所，碩士論文，民國97年。

徐之強、黃裕烈(2005)，運用領先指標預測景氣變化之研究，行政院經濟建設委員會研究成果報告，報告編號94-040.210

陳仕偉、沈中華(2003)金融領先指標與實質領先指標訊息一致嗎？台灣領先指標的實證分析，《人文及社會科學集刊》vol.15:4，pp627-660


Burns, A.F. and Mitchell, W.C. (1946), “Measuring Business Cycles.” New York: NationalBureau of Economic Research.

Barhoumi, K., Darne, O. and Ferrara, L. (2013), “Testing the Number of Factors: An Empirical Assessment for a Forecasting Purpose.” Oxford Bulletin of Economics and Statistics, 75: 64–79.

Chauvet, Marcelle, and Simon Potter (2005), “Forecasting  Recessions Using the Yield Curve” Journal of Forecasting,24, 77-103

Camacho, M., Prez-Quiros,G., (2002). “This is what the leading indicators lead”. Journal of Applied Econometrics 17,61-80

Cecchetti, S. G., R. S. Chu and C. Steindel (2000), “The Unreliability of Inflation Indicators”, Current Issues in Economics and Finance 6: 1-6.

Diebold, F. X. and Rudebusch, G. D. (1991a).“Forecasting output with the composite leading index: a real-time analysis.” Journal of the American Statistical  Association,86 ,603-610.

Diebold, F. X. and Rudebusch, G. D. (1991b).“Turning point prediction with the composite leading index: a0n ex ante analysis”. In K. Lahiri and G. H. Moore (Eds.), “Leading Economic Indicators: 	New Approaches and Forecasting Records”, 231-256. Cambridge University Press, U.K..

Diebold, F. X. and Rudebusch, G. D. (1996). “Measuring business cycles :A modern perspective.” 
The Review of Economics and Statistics 78, 67-77.

Diebold, F. X. and Rudebusch, G. D. (1989). “Scoring the leading indicator.” Journal of Business 62,369-391.

Estrella, Arturo, and Frederic S. Mishkin, (1998) “Predicting U.S. Recession: Financial Variables as Leading Indicators” The Review of Economics and Statistics, 80,45-61

Hamilton, J. D. (1989), “A new approach to the economic analysis of nonstationary time seriesand the business cycle,” Econometrica, 57, 357–384

Hamilton, J. D. and Perez-Quiros, G. (1996). “What do leading indicators lead?” Journal of Business 69, 27-49.

Kauppi, H., Saikkonen,P., n.d. “Predicting U.S. Recessions with Dynamic 	Binary Response Models.” The Review of Economics and Statistics 90,777-791

Layton, A.P(1996), “Dating and Predicting Phase Changes in the U.S. Business Cycle,” International Journal of Forecasting, 12(3), 417-428

Summers, L.H., n.d. “The Scientific Illusion in Empirical Macroeconomics.” 
Scandinavian Journal of Economics 93，123-148	

Sargent, T. J,. and Sims, C. A. (1977), “Business Cycle Modeling Without Pretending to Have Too Much A Priori Economic Theory,” in New Methods in Business Cycle Research, eds. C. Sims et al., Minneapolis: Federal Reserve Bank of Minneapolis.

Stock, James H. and Mark W. Watson (1999), “Forecasting Inflation.” Journal of Monetary Economics, v. 44, 293-335.

Tong, H. (1990). “Non-Linear Time Series: A Dynamic System Approach” Oxford: Oxford University Press.