Error: unknown column "tau" about bumbl HOT 6 CLOSED

When did you install bumbl? I just updated it earlier this week, although I'm not sure it would change anything in this example...
The warning about not being able to find starting values sounds like it's coming from glm() and I'm not sure why.

from bumbl.

Just installed today. It's as if the glm() call is looking for a column named "tau" instead of "week"

from bumbl.

I'm at EntSoc this week (any chance you're here too?), but I'll take a look at it when I get back and see if I can reproduce it. Thanks for trying it out!

from bumbl.

Unfortunately I am not going this year - opted out to stay and finish thesis! No problem, I'll watch this thread. Feel free to holler at my if you want some additional beta testing - I told Elizabeth at BOMBUSS I'd be happy to do so.

from bumbl.

Note to self: Check out glm2 package and see if it might be more stable to finding starting values.

from bumbl.

I'm not sure, but I suspect it has something to do with you having two data points of mass for each week. Try just using date as the response variable and time variable. I agree the "unknown column tau" is misleading, so I'm going to work on a better error message for situations when the underlying glm() fails.

from bumbl.