Replication Data for: Error Correction Methods with Political Time Series

While traditionally considered for non-stationary and cointegrated data, De Boef and Keele (2008) suggest applying a General Error Correction Model to stationary data with or without cointegration. The GECM has since become extremely popular in political science but practitioners have confused essential points. For one, the model is treated as perfectly flexible when, in fact, the opposite is true. Time series of various orders of integration – stationary, non-stationary, explosive, near- and fractionally-integrated – should not be analyzed together but researchers consistently make this mistake. That is, without equation balance the model is misspecified and hypothesis tests and long-run-multipliers are unreliable. Another problem is that the error correction term’s sampling distribution moves dramatically depending upon the order of integration, sample size, number of covariates, and the boundedness of Yt. This means that practitioners are likely to overstate evidence of error correction, especially when using a traditional t-test. We evaluate common GECM practices with six types of data, 746 simulations, and five paper replications.

尽管传统上广义误差修正模型（General Error Correction Model，GECM）多用于处理非平稳与协整数据，但De Boef与Keele（2008）提出，该模型同样可应用于存在或不存在协整关系的平稳数据。自此之后，GECM在政治学领域得到了极为广泛的应用，但实务研究者却对其核心要点存在诸多误解。其一，该模型常被认为具有完全的灵活性，但实际情况恰好相反。不同单整阶数（order of integration）的时间序列——包括平稳、非平稳、爆炸型、近单整及分整序列——不应被联合分析，但研究者却屡屡犯下这一错误。换言之，若不满足方程平衡性，模型将出现设定偏误，此时假设检验与长期乘数的结果将不再可靠。其二，误差修正项的抽样分布会随单整阶数、样本量、协变量数量以及被解释变量Y_t的有界性发生显著变化。这意味着实务研究者很可能会高估误差修正的证据强度，在使用传统t检验时这一问题尤为突出。本研究通过六类数据集、746次模拟仿真以及五项已发表研究的复制验证，对当前主流的GECM应用实践进行了评估。