Skip to content

- help - predicting with glmnet/lars for dataframes with different nrow then the train set

2 messages · eitan lavi, Hadley Wickham

#
On Mon, Mar 16, 2009 at 7:21 PM, eitan lavi <lavi.eitan at gmail.com> wrote:
I don't know if this is the problem or not (you didn't supply a
reproducible example), but I'd expect your call to be:

log.1 <- glm(TL ~ ., data = temp.data , family = binomial , x = TRUE,  y = TRUE)

i.e. when you supply a data frame you don't explicitly use it in the formula.

Hadley