傳統景氣循環認定方法存在時間落後問題，如我國近3次景氣循環，國家發展委員會在轉折點發生約兩年後才會認定，降低景氣循環實務決策應用價值。本文採用國發會七項同時指標，資料期間涵蓋1999年1月至2024年12月，透過EM演算法估計模型參數，並結合機率門檻與景氣循環判定標準進行樣本外即時預測。研究設定景氣循環具有擴張與衰退兩種狀態，運用擴展窗口法模擬政策制定者在資訊不完全條件下的即時判斷情境。實證結果顯示，模型成功識別台灣樣本外所涵蓋的五次景氣轉折點，與國發會官方認定的平均誤差為0.8個月。結合景氣循環判定標準後，大幅降低假警報 (false positives) 問題。相較於官方發布時間，模型平均能提前21個月提供景氣轉折預警，其中特別在COVID-19疫情期間提前14個月預警第15次景氣循環衰退認定上。本研究為高維度狀態轉換因子模型相關領域供新的分析工具，並建立具實用價值的景氣轉折即時認定框架。

Traditional business cycle dating methods have a problem of time lag. For example, in the most recent three business cycles in Taiwan, the National Development Council (NDC) recognized the turning points approximately two years after their actual occurrence, which reduces the practical value of business cycle information in decision-making. This study uses the seven coincident indicators published by the NDC, covering the data period from January 1999 to December 2024. Model parameters are estimated through the Expectation Maximization algorithm, and out-of-sample real-time prediction is conducted by combining probability thresholds and business cycle dating rules. The study assumes that the business cycle consists of two states: expansion and recession, and applies the expanding window method to simulate the real-time judgment scenario of policymakers under incomplete information. The empirical results show that the model successfully identifies the five business cycle turning points in Taiwan covered by the out-of-sample period, with an average deviation of 0.8 months compared to the official dates recognized by the NDC. After incorporating business cycle dating criteria, the issue of false positives is significantly reduced. Compared to the official announcement dates, the model can on average provide early warning signals of turning points 21 months in advance, including a 14-month lead in predicting the 15th recession recognized during the COVID-19 pandemic. This study provides a new analytical tool for the field of high-dimensional regime-switching factor models, and establishes a practical real-time identification framework for business cycle turning points.

Bai, J. (2003). Inferential theory for factor models of large dimensions. Econometrica, 71(1), 135–171.
Bai, J., & Ng, S. (2002). Determining the number of factors in approximate factor models. Econometrica, 70(1), 191–221.
Banerji, A. (1999). The three Ps: Simple tools for monitoring economic cycles. Business Economics, 34(4), 72–76.
Breitung, J., & Eickmeier, S. (2011). Testing for structural breaks in dynamic factor models. Journal of Econometrics, 163(1), 71–84.
Bry, G., & Boschan, C. (1971). Programmed selection of cyclical turning points. In Cyclical analysis of time series: Selected procedures and computer programs (pp. 7–63). NBER.
Burns, A. F., & Mitchell, W. C. (1946). Measuring business cycles. National bureau of economic research.
Chauvet, M. (1998). An econometric characterization of business cycle dynamics with factor structure and regime switching. International Economic Review, 39(4), 969–996.
Chauvet, M., & Piger, J. (2008). A comparison of the real-time performance of business cycle dating methods. Journal of Business & Economic Statistics, 26(1), 42–49.
Cheng, X., Liao, Z., & Schorfheide, F. (2016). Shrinkage estimation of high-dimensional factor models with structural instabilities. The Review of Economic Studies, 83(4), 1511–1543.
Diebold, F. X., & Rudebusch, G. D. (1994). Measuring business cycles: A modern perspective (Vol. 4643). National Bureau of Economic Research Cambridge, Mass., USA.
Engle, R., & Watson, M. (1981). A one-factor multivariate time series model of metropolitan wage rates. Journal of the American Statistical Association, 76(376), 774–781.
Filardo, A. J. (1994). Business-cycle phases and their transitional dynamics. Journal of Business & Economic Statistics, 12(3), 299–308.
Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica, 57(2), 357–384.
Hamilton, J. D. (1990). Analysis of Time Series subject to changes in Regime. Journal of Econometrics, 45(1), 39–70.
Hamilton, J. D. (2011). Calling recessions in real time. International Journal of Forecasting, 27(4), 1006–1026.
Kim, C. J. (1994). Dynamic linear models with markov-switching. Journal of Econometrics, 60(1), 1–22.
Kim, C. J., & Nelson, C. R. (1998). Business cycle turning points, a new coincident index, and tests of duration dependence based on a dynamic factor model with regime switching. Review of Economics and Statistics, 80(2), 188–201.
Kim, M.-J., & Yoo, J.-S. (1995). New index of coincident indicators: A multivariate Markov switching factor model approach. Journal of Monetary Economics, 36(3), 607–630.
Lam, P.-S. (1990). The hamilton model with a general autoregressive component: Estimation and comparison with other models of economic time series: Estimation and comparison with other models of economic time series. Journal of Monetary Eco- nomics, 26(3), 409–432.
Liu, X., & Chen, R. (2016). Regime-switching factor models for high-dimensional time series. Statistica Sinica, 26(4), 1427–1451.
Pelger, M., & Xiong, R. (2022). State-varying factor models of large dimensions. Journal of Business & Economic Statistics, 40(3), 1315–1333.
Stock, J. H., & Watson, M. W. (1989). New indexes of coincident and leading economic indicators. NBER macroeconomics annual, 4, 351–394.
Stock, J. H., & Watson, M. W. (2002). Forecasting using principal components from a large number of predictors. Journal of the American Statistical Association, 97(460), 1167–1179.
Urga, G., & Wang, F. (2024). Estimation and inference for high dimensional factor model with regime switching. Journal of Econometrics, 241(2), 105752.
朱浩榜（2021），〈即時認定台灣的景氣轉折〉，《經濟論文叢刊》，49(3)，頁 335–370。
陳淑玲、黃裕烈（2015），〈臺灣景氣基準循環指數之檢討與改進〉，《Taiwan Economic Forecast & Policy》，46(1)。
陳惠薇（2009），〈我國第 11 次景氣循環高峰之認定與研析〉，《Economic Research》，9，頁 1。