Cointegration and long-horizon forecasting

被引：74
作者：
Christoffersen, PF [1 ]
Diebold, FX
机构：
[1] McGill Univ, Fac Management, Montreal, PQ H3A 1G5, Canada
[2] Univ Penn, Dept Econ, Philadelphia, PA 19104 USA
[3] Natl Bur Econ Res, Cambridge, MA 02138 USA
来源：
JOURNAL OF BUSINESS & ECONOMIC STATISTICS | 1998年 / 16卷 / 04期
关键词：
integration; loss function; prediction; unit root;
D O I：
10.2307/1392613
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
We consider the forecasting of cointegrated variables, and we show that at long horizons nothing is lost by ignoring cointegration when forecasts are evaluated using standard multivariate forecast accuracy measures. In fact, simple univariate Box-Jenkins forecasts are just as accurate. Our results highlight a potentially important deficiency of standard forecast accuracy measures-they fail to value the maintenance of cointegrating relationships among variables-and we suggest alternatives that explicitly do so.
引用
收藏
页码：450 / 458
页数：9
相关论文
共 31 条
  • [11] FORECASTING IN COINTEGRATED SYSTEMS
    CLEMENTS, MP
    HENDRY, DF
    [J]. JOURNAL OF APPLIED ECONOMETRICS, 1995, 10 (02) : 127 - 146
  • [12] CLEMENTS MP, 1994, NONSTATIONARY TIME S, P9
  • [13] Diebold F., 1996, Handbook of statistics, P241
  • [14] COMPARING PREDICTIVE ACCURACY
    DIEBOLD, FX
    MARIANO, RS
    [J]. JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 1995, 13 (03) : 253 - 263
  • [15] DIEBOLD FX, 1998, INT EC REV, V39
  • [16] FORECASTING AND TESTING IN CO-INTEGRATED SYSTEMS
    ENGLE, RF
    YOO, BS
    [J]. JOURNAL OF ECONOMETRICS, 1987, 35 (01) : 143 - 159
  • [17] Granger CWJ, 1996, J APPL ECONOM, V11, P455, DOI 10.1002/(SICI)1099-1255(199609)11:5<455::AID-JAE408>3.0.CO
  • [18] 2-E
  • [19] Granger CWJ, 1986, FORECASTING EC TIME
  • [20] Hoffman DL, 1996, J APPL ECONOM, V11, P495, DOI 10.1002/(SICI)1099-1255(199609)11:5<495::AID-JAE407>3.0.CO
1234