[R] GLM/VGAM exponential weighting and sequential regression

Benoit J benoit_jottreau at yahoo.fr
Sat Jan 12 15:45:23 CET 2008


I have a data.frame with first column date (possibly several rows with same

second column X1 and third X2 for example

i would like to regress X1 on X2 but with exponential weight i.e. give more
weights to last observations
and i would like to do this in sequential mode i.e for first 100 values then
first 110 values then first 120 for example and etc.

is there an option in glm or vglm in vgam package to do this?

and in rrvglm function i would to do same but with the option to keep
constraints matrices constant from week to week.

If somebody could help me, a lot of thanks.

Benoit J.
R Fan

View this message in context: http://www.nabble.com/GLM-VGAM-exponential-weighting-and-sequential-regression-tp14774166p14774166.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list