« first day (2174 days earlier)
← previous day
next day →
last day (2841 days later) »
Kodiologist
7:06 PM
@IuliusCurt Yes, because training-set accuracy is at 100%, the model is probably underdetermined (and hence non-identifiable), which suggests you either need more training data or a simpler model.
3 hours later…
Silverfish
10:16 PM
Someone asked me today whether it was correct to say their test was significant, since the p-value was below 1.
3
I suppose at a certain level of significance, that is actually true.
« first day (2174 days earlier)
← previous day
next day →
last day (2841 days later) »
all rooms
Transcript for
Jul
29
Jul '16
30
Jul
31
Ten fold
CrossValidated's general room for gossip, grumbles, and idle c...
join this room
about this room
00:00
06:00
12:00
18:00
all times are UTC
site design / logo © 2024 Stack Exchange Inc;
legal
mobile