#### DMCA

## Testing for Common Trends (1988)

Venue: | Journal of the American Statistical Association |

Citations: | 464 - 7 self |

### Citations

5195 | Convergence of Probability Measures - Billingsley - 1968 |

2684 | Co-integration and error correction: Representation, estimation, and testing - Engle, Granger - 1987 |

2627 |
Distribution of the estimators for autoregressive time-series with a unit root
- Dickey, Fuller
- 1979
(Show Context)
Citation Context ...l special cases of this testing problem have been considered elsewhere. The case that has received the most attention has been testing for 1 versus 0 unit roots in a univariate time series (e.g., see =-=Dickey and Fuller 1979-=-; Fuller 1976; Phillips 1987; Solo 1984). In a multivariate setting, a test of k = 1 versus m = 0 was developed by Fountis and Dickey (1986) for processes with a VAR representation with iid normal err... |

801 |
Introduction to Statistical Time Series.
- Fuller
- 1976
(Show Context)
Citation Context ...testing problem have been considered elsewhere. The case that has received the most attention has been testing for 1 versus 0 unit roots in a univariate time series (e.g., see Dickey and Fuller 1979; =-=Fuller 1976-=-; Phillips 1987; Solo 1984). In a multivariate setting, a test of k = 1 versus m = 0 was developed by Fountis and Dickey (1986) for processes with a VAR representation with iid normal errors. Engle an... |

766 | Trends and Random Walks in Macroeconomic Time Series: Some Evidence and Implications,” - Nelson, Plosser - 1982 |

583 | A New Approach to Decomposition of Economic Time Series into Permanent and Transitory Components with Particular Attention to Measurement of the Business Cycle,” - Beveridge, Nelson - 1981 |

421 | Time Series Regressions with a Unit Root.”
- Phillips
- 1987
(Show Context)
Citation Context ...em have been considered elsewhere. The case that has received the most attention has been testing for 1 versus 0 unit roots in a univariate time series (e.g., see Dickey and Fuller 1979; Fuller 1976; =-=Phillips 1987-=-; Solo 1984). In a multivariate setting, a test of k = 1 versus m = 0 was developed by Fountis and Dickey (1986) for processes with a VAR representation with iid normal errors. Engle and Granger (1987... |

251 | Asymptotic Properties of Least Squares Estimators of Co integrating Vectors", manuscript, - STOCK - 1984 |

205 | Econometric Modelling of the Aggregate Time Series Relationship Between Consumers' Expen diture and Income in the United Kingdom", - DAVIDSON, HENDRY, et al. - 1978 |

151 | Wages and prices in the United Kingdom: a study in econometric methodology. Econometric Analysis for National Economic Planning, - Sargan - 1964 |

145 | Trends and Cycles in Macroeconomic Time Series," - Harvey - 1985 |

125 | Limiting distributions of least squares estimates of unstable autoregressive processes.” - Chan, Wei - 1988 |

125 | Multiple Time Series Regression with Integrated Processes. - Phillips, Durlauf - 1986 |

59 | Statistical Confluence Analysis by Means of Complete Regression Systems. - Frisch - 1934 |

55 | Canonical Analysis of Multiple Time Series. - Box, Tiao - 1977 |

14 |
The Order of Differencing in ARIMA Models,"
- SOLO
- 1984
(Show Context)
Citation Context ...nsidered elsewhere. The case that has received the most attention has been testing for 1 versus 0 unit roots in a univariate time series (e.g., see Dickey and Fuller 1979; Fuller 1976; Phillips 1987; =-=Solo 1984-=-). In a multivariate setting, a test of k = 1 versus m = 0 was developed by Fountis and Dickey (1986) for processes with a VAR representation with iid normal errors. Engle and Granger (1987) proposed ... |

12 | Testing for a Unit Root Nonstationarity in Multivariate Autoregressive Time Series,”Annals of - Fountis, Dickey - 1989 |

4 | Stochastic Trend and Economic Fluctuations,” Working Paper version - King, Plosser, et al. - 1987 |

2 |
Time Series Analysis and Theory
- Brillinger
- 1975
(Show Context)
Citation Context ... (1 - L)-1(C(L) - C(1)) so that Cj* = -E'=j,I Ci. Because a'C(l) = 0 and a'u = 0, it follows that Zt a'Xt = a'Xo + a'C*(L)GlI2vt. (2.3) With the additional assumption in (2.1) that C(L) is 1summable (=-=Brillinger 1981-=-), C*(L) is absolutely summable and Zt has bounded variance. The cointegrated process Xt has an alternative representation in terms of a reduced number of common random walks plus a stationary compone... |

1 | Testing for Common Trends: Technical Appendix - Stock, Watson - 1988 |