Excessive division by df in `generate.TSLM()` to obtain the variance of innovations?

[zouharj]

In generate.TSLM(), the variance of generated (non-bootstrapped) innovations is obtained as x$sigma2 / x$df.residual:

fable/R/lm.R

Line 331 in a9404d8

vars <- x$sigma2 / x$df.residual

Correct me if I'm wrong, but I believe that plain x$sigma2 is in fact the variance we would like to use (sigma2 is obtained as rss/df, I don't see the point of further division by df).

[robjhyndman]

Thanks. Now fixed in 79d5a50