Dear R Users, R Core Team,
I currently wonder how to predict the probability of an event with new data
resulting from a finite mixture.
I read the documentation of the flexmix package and the examples of
applications provided on CRAN but I could not find how to predict (except
"manually" but I am looking for a simpler solution) the final probability of
the mixture (for each individual) with new data (I mean data different from the
ones I used to build the model).
I should have missed something but basically, I am fitting a 2-components
mixture model with logistic weights and logistic components (and different
explanatory variables, no identifiability problem). The flexmix object is then
used in predict() function with 'newdata' in argument, and the predictions with
these new data are obviously different depending on the component which is
assigned to new observations.
My question is: how can I access the information on clustering the new
observations (if I understood well, predictions are the predictions of the
event probability for each individual and each component, but these are not
predictions for cluster assignment...) ?
Thank you very much in advance for your answers,
Sincerely,
Xavier M.
Une messagerie gratuite, garantie à vie et des services en plus, ça vous
tente ?
Je crée ma boîte mail www.laposte.net
[[alternative HTML version deleted]]
______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
