Publikation: Working paper › Forskning

- David F. Hendry, Oxford University, Storbritannien
- Søren Johansen
- Carlos Santos, Portuguese Catholic University, Porto, Portugal

- Institut for Økonomi

We consider selecting a regression model, using a variant of Gets, when there are more variables

than observations, in the special case that the variables are impulse dummies (indicators) for every

observation. We show that the setting is unproblematic if tackled appropriately, and obtain the

finite-sample distribution of estimators of the mean and variance in a simple location-scale model

under the null that no impulses matter. A Monte Carlo simulation confirms the null distribution,

and shows power against an alternative of interest.

than observations, in the special case that the variables are impulse dummies (indicators) for every

observation. We show that the setting is unproblematic if tackled appropriately, and obtain the

finite-sample distribution of estimators of the mean and variance in a simple location-scale model

under the null that no impulses matter. A Monte Carlo simulation confirms the null distribution,

and shows power against an alternative of interest.

Originalsprog | Engelsk |
---|---|

Udgivelsessted | Aarhus |

Udgiver | Institut for Økonomi, Aarhus Universitet |

Antal sider | 17 |

Status | Udgivet - 2007 |

Se relationer på Aarhus Universitet Citationsformater

ID: 10570860