Time series models are a common tool in both environmetrics and econometrics. Dynamic eects are accommodated by the inclusion of lagged variables. Tests of null hypotheses involving `long-run' eects are not invariant and, surprisingly, the most commonly used form involves a non-linear hypothesis whe
Aggregation and the long run properties of economic time series
✍ Scribed by Gábor Kőrösi; László Lovrics; László Mátyás
- Publisher
- Elsevier Science
- Year
- 1995
- Tongue
- English
- Weight
- 493 KB
- Volume
- 39
- Category
- Article
- ISSN
- 0378-4754
No coin nor oath required. For personal study only.
✦ Synopsis
The aggregation problem is a well-known difficulty in macroeconometric modelling. It is frequently assumed in these models that the behaviour of economic agents is uniform. Thus the behaviour of a single agent characterizes the aggregate behaviour of the agents (representative agent). However, there may always be some "outliers", some uncharacteristically behaving agents. Such outliers may well determine the time dynamics of the aggregate time series. The paper presents different Monte Carlo experiments to demonstrate this feature. This phenomenon may have an utmost significance in models assuming the cointegration of the variables,
📜 SIMILAR VOLUMES