31 May
2007
31 May
'07
1:31 p.m.
Hi
the problem in your first example is that you don't really have a
cross sectional time series data set, but just time series. Therefore
you cannot set intercs=TRUE since you don't have any crosssections to
interact with.
For the second error, check the list of your variables again to see
if you don't have any nominal (factor) variables that aren't properly
declared.
Raffael
__________________________________
Raffael Himmelsbach
Institut d'Etudes Politiques et Internationales
Batiment Anthropôle, Bureau 5128
Université de Lausanne
CH-1015 Lausanne
Phone: +41 21 692 31 76
Cell: +41 79 756 85 10
On 31.05.2007, at 08:36, Falko Düsterhöft wrote:
hi,
i have a problem with amelia II on time series like this:
Date Value
1 1988-01-02 2.490
2 1988-02-02 2.400
3 1988-03-01 2.190
4 1988-04-05 1.720
5 1988-05-02 1.860
6 1988-05-26 2.000
if i try this in R:
amelia(m_reihe,m=5,ts=1,cs=2,polytime=3,intercs=TRUE)
i get this error message:
Amelia Error Code: 28
There are too many cross-sections in the data to use an
interaction between polynomial of time and the cross-section.
if i try this in R:
amelia(m_reihe,m=5,ts=1,cs=2,polytime=3)
i get this message from R:
Amelia Error Code: 37
You have a "factor" variable in the data. You may
have wanted to set this as a ID variable to remove it
from the imputation model or as an ordinal or nominal
variable to be imputed. Please set it as either and
try again.
what ist the problem? cant amelia handle this data? what have i to
do that it could handle it?
or do you know an other package for multiple imputation in time
series???
best regards falko
_______________________________________________________________
SMS schreiben mit WEB.DE FreeMail - einfach, schnell und
kostenguenstig. Jetzt gleich testen! http://f.web.de/?mc=021192
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?
info=amelia