
handle: 10419/32036
Ein wichtiges Problem in der statistischen Analyse ist die Auswahl eines passenden Mo-dells. Im Kontext linearer ARIMA-Modelle kann gezeigt werden, dass - die Gültigkeit bestimmter Regularitätsbedingungen vorausgesetzt - die Minimierung des Schwarz-Kriteriums zu einer konsistenten Wahl der Anzahl der Parameter in einem Modell führt, wohingegen die Schätzung der Parameterzahl mit Hilfe des Akaike-Kriteriums tendenziell zu große Modelle liefert. Ziel dieser Analyse ist es, mit Hilfe von Monte-Carlo-Experimenten die Eigenschaften des Akaike- und des Schwarz-Informationskriteriums zu untersuchen, wenn der datengenerierende Prozess GARCH-Störungen aufweist.
An important problem in statistical practise is the selection of a suitable statistical model. In the context of linear ARIMA-models it can be shown that - the validity of certain regu-larity conditions presupposed - the minimization from Black-criterion leads to a consistent choice of the parameters in a model whereas the estimation of the parameter number with the Akaike-criterion tendentious leads to too large models. Goal of this analysis is to examine with Monte Carlo experiments the characteristics of the Akaike- and of the Black-criterion if the data generating process exhibits GARCH-effects.
ddc:330
ddc:330
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
