Remarks on the SEECM
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we calculate mean and variance of least square estimators (LSEs) of the coefficients in the single equation error correction model (SEECM). We compare them with those in the linear regression model (LRM) to assess the usefulness of the SEECM. We consider three cases that assume different settings for LRM. Our results show that the SEECM is preferable for trend plus random walk error but not for trend plus iid error. For random exploratory variable with error, the SEECM is preferable, depending on the correlation structure of random exploratory variable.
Abstract
In this paper, we calculate mean and variance of least square estimators (LSEs) of the coefficients in the single equation error correction model (SEECM). We compare them with those in the linear regression model (LRM) to assess the usefulness of the SEECM. We consider three cases that assume different settings for LRM. Our results show that the SEECM is preferable for trend plus random walk error but not for trend plus iid error. For random exploratory variable with error, the SEECM is preferable, depending on the correlation structure of random exploratory variable.
참고문헌 (4)
- Davidson JD, "Econometric modelling of the aggregate time series relationaship between consumers’ expenditures and income in the United Kingdom", Economic Journal, 88, pp.661~692 (1978)
- Engle RF, "Co-integration and error correction: representation, estimation and testing", Econometrica, 55, pp.251~276 (1987)
- Beck N., "Comparing dynamic specifications: the case of presidential approval", Political Analysis, 3, pp.51~87 (1991)
- Durr RH., "An essay on cointegration and error correction models", Political Analysis, 4, pp.185~228 (1992)